Publications | Iana Atanassova, Ph.D.

2025

Journal Articles

Annotating scientific uncertainty: A comprehensive model using linguistic patterns and comparison with existing approaches

Panggih Kusuma Ningrum, Philipp Mayr, Nina Smirnova, and Iana Atanassova

Journal of Informetrics, May 2025

Abs DOI Bib

We present UnScientify, a system designed to detect scientific uncertainty in scholarly full text. The system utilizes a weakly supervised technique to identify verbally expressed uncertainty in scientific texts and their authorial references. The core methodology of UnScientify is based on a multi-faceted pipeline that integrates span pattern matching, complex sentence analysis and author reference checking. This approach streamlines the labeling and annotation processes essential for identifying scientific uncertainty, covering a variety of uncertainty expression types to support diverse applications including information retrieval, text mining and scientific document processing. The evaluation results highlight the trade-offs between modern large language models (LLMs) and the UnScientify system. UnScientify, which employs more traditional techniques, achieved superior performance in the scientific uncertainty detection task, attaining an accuracy score of 0.808. This finding underscores the continued relevance and efficiency of UnScientify’s simple rule-based and pattern matching strategy for this specific application. The results demonstrate that in scenarios where resource efficiency, interpretability, and domain-specific adaptability are critical, traditional methods can still offer significant advantages.
@article{Ningrum2025b, author = {Ningrum, Panggih Kusuma and Mayr, Philipp and Smirnova, Nina and Atanassova, Iana}, title = {Annotating scientific uncertainty: A comprehensive model using linguistic patterns and comparison with existing approaches}, doi = {10.1016/j.joi.2025.101661}, issn = {1751-1577}, number = {2}, volume = {19}, author+an = {1=student;4=me}, journal = {Journal of Informetrics}, month = may, publisher = {Elsevier BV}, year = {2025} }
Etudier l’incertitude dans les articles scientifiques : mise en perspective d’une méthode linguistique

Panggih Kusuma Ningrum, Nicolas Gutehrlé, and Iana Atanassova

Revue des Nouvelles Technologies de l’Information, May 2025

Abs Bib

L’incertitude fait partie intégrante du processus de recherche scientifique et est inhérente à la construction de nouvelles connaissances. Dans cet article, nous examinons la manière dont l’incertitude est exprimée dans les articles scientifiques et proposons un cadre d’annotation rendant compte des différentes dimensions de cette notion. L’incertitude scientifique est définie ici comme l’expression d’un manque de connaissance ou d’un manque de précision dans les informations sur un sujet ou un concept identifié. Nous proposons un jeu de données de référence (gold standard), composé de 1 839 phrases d’articles scientifiques annotées manuellement et provenant de plusieurs disciplines. Nous proposons également une approche à base de connaissances linguistiques pour l’annotation automatique des articles et pour la détection et la catégorisation de l’incertitude scientifique. Nous comparons l’efficacité de notre approche en termes de scores de Précision, Rappel et F1 aux méthodes de prompts few-shot réalisées via les Grands Modèles de Langue Phi-3.5 et Llama 3 pour la même tâche d’annotation. Cette évaluation comparative montre des scores similaires entre les approches, allant jusqu’à des scores F1 de 0,858 pour notre approche.
@article{Ningrum2025c, author = {Ningrum, Panggih Kusuma and Gutehrlé, Nicolas and Atanassova, Iana}, title = {Etudier l'incertitude dans les articles scientifiques : mise en perspective d'une méthode linguistique}, pages = {111--122}, volume = {Extraction et Gestion des Connaissances, RNTI-E-41}, author+an = {3=me;2=student;1=student}, journal = {Revue des Nouvelles Technologies de l'Information}, year = {2025}, }

Conference Papers

Is There Life on Mars? Studying the Context of Uncertainty in Astrobiology

Iana Atanassova, Panggih Kusuma Ningrum, Nicolas Gutehrlé, Francis Lareau, and Christophe Malaterre

In 20^th International Conference of the International Society for Scientometrics and Informetrics (ISSI 2025), Jun 2025

Abs Bib

While science is often portrayed as producing reliable knowledge, scientists tend to express caution about their claims, acknowledging nuances and doubt, all the more so in novel domains of research paved with unknowns. Uncertainty is an intrinsic aspect of scientific inquiry, particularly in recent fields such as astrobiology, which tackles numerous hard questions about the origin, evolution, and distribution of life on Earth and elsewhere. Mapping uncertainty in science matters for achieving a more accurate understanding of scientific knowledge. It also helps identify research domains at the frontiers of knowledge where unknowns are the most salient. In this article, we investigate the presence, distribution and context of uncertainty in the field of astrobiology. We analyze a comprehensive corpus of 3,698 research articles published in three major journals in the domain from 1968 to 2020. We use a linguistically motivated approach to identify expression of uncertainty in article full text. The corpus was further segmented into research topics using Latent Dirichlet Allocation (LDA) to investigate variations in uncertainty across subfields and over time. Our findings show that, while uncertainty has remained relatively stable over the 50 years covered by the corpus, constituting 20–25% of sentences on average, it varies significantly across research fields, highlighting areas where unknowns, doubts and speculations are more prevalent. The analysis also highlights relationships between expression of uncertainty and rhetorical structure. Indeed, higher uncertainty levels were observed in the beginning (introductions) and towards the end (conclusions) of research articles, while middle sections contained less uncertainty. Abstracts also tended to express a slightly higher level of uncertainty compared to main texts, especially with greater variability, suggesting their role in summarizing research and highlighting unknowns. To investigate the context of uncertainty, a lexical analysis was conducted to identify nouns most frequently associated with uncertainty within each topic. Terms such as “life,” “planet,” and “Mars” were found to be strongly associated with uncertainty. Conversely, terms related to experimentation and measurement, such as “sample” and “spectrum,” were linked to an absence of uncertainty, pointing at a dichotomy between speculative and evidence-based lines of inquiry. The findings contribute to a better understanding of the field of astrobiology and exemplify the relevance of the proposed method to identify uncertainty- related concepts in corpora of full text publications. They also offer a foundation for future comparative studies across disciplines.
@inproceedings{Atanassova2025, author = {Atanassova, Iana and Ningrum, Panggih Kusuma and Gutehrlé, Nicolas and Lareau, Francis and Malaterre, Christophe}, booktitle = {20th International Conference of the International Society for Scientometrics and Informetrics (ISSI 2025)}, title = {{Is There Life on Mars? Studying the Context of Uncertainty in Astrobiology}}, address = {Yerevan, Armenia}, author+an = {1=me;2=student;3=student}, month = jun, year = {2025}, }

Datasets

AURORA-MESS: Annotated Uncertainty and Reference in Open Research Articles for Multidisciplinary and Empirical Social Science

Panggih Kusuma Ningrum and Iana Atanassova

Mar 2025

Abs DOI Bib

The AURORA-MESS dataset offers valuable insights into the representation of uncertainty in scientific literature across various domains, along with associated authorial references. Researchers and practitioners can use this dataset to study and analyze the variations of uncertainty expressions in scholarly discourse. This dataset contains sentences extracted from articles in a wide range of fields, covering both Science, Technology, and Medicine (STM); and Social Sciences and Humanities (SSH) and annotated with respect to uncertainty in science. The dataset is derived from PubMed, Scopus, Web of Science (WoS) and Social Science Open Access Repository (SSOAR). It has been produced as part of the ANR InSciM (Modelling Uncertainty in Science) project.
@dataset{Ningrum2025, author = {Ningrum, Panggih Kusuma and Atanassova, Iana}, title = {AURORA-MESS: Annotated Uncertainty and Reference in Open Research Articles for Multidisciplinary and Empirical Social Science}, doi = {10.5281/zenodo.15001250}, url = {https://doi.org/10.5281/zenodo.15001250}, version = {ver1}, author+an = {2=me;1=student}, month = mar, publisher = {Zenodo}, year = {2025}, }

MUSIC-OpRA: Multidimensional Uncertainty in Scientific Interdisciplinary Corpora for Open Research Article

Panggih Kusuma Ningrum, Iana Atanassova, and Nicolas Gutehrlé

Apr 2025

DOI Bib

@dataset{Ningrum2025a,
  author = {Ningrum, Panggih Kusuma and Atanassova, Iana and Gutehrlé, Nicolas},
  title = {MUSIC-OpRA: Multidimensional Uncertainty in Scientific Interdisciplinary Corpora for Open Research Article},
  doi = {10.5281/zenodo.15173356},
  url = {https://doi.org/10.5281/zenodo.15173356},
  version = {ver1},
  author+an = {2=me;1=student;3=student},
  month = apr,
  publisher = {Zenodo},
  year = {2025},
}

2024

Journal Articles

Annotation of scientific uncertainty using linguistic patterns

Panggih Kusuma Ningrum and Iana Atanassova

Scientometrics, May 2024

Abs DOI Bib

Scientific uncertainty is an integral part of the research process and inherent to the construction of new knowledge. In this paper, we investigate the ways in which uncertainty is expressed in articles and propose a new interdisciplinary annotation framework to categorize sentences containing uncertainty expressions along five dimensions. We propose a method for the automatic annotation of sentences based on linguistic patterns for identifying the expressions of scientific uncertainty that have been derived from a corpus study. We processed a corpus of 5956 articles from 22 journals in three different discipline groups, which were annotated using our automatic annotation method. We evaluate our annotation method and study the distribution of uncertainty expressions across the different journals and categories. The results show a predominant concentration of the distribution of the scientific uncertainty expressions in the Results and Discussion section (71.4%), followed by 12.5% of expressions in the Background section, and the largest proportion of uncertainty expressions, approximately 70.3%, are formed as author(s) statements. Our research contributes methodological advances and insights into the diverse manifestations of scientific uncertainty across disciplinary domains and provides a basis for ongoing exploration and refinement of the understanding of scientific uncertainty communication.
@article{Ningrum2024, author = {Ningrum, Panggih Kusuma and Atanassova, Iana}, title = {{Annotation of scientific uncertainty using linguistic patterns}}, doi = {10.1007/s11192-024-05009-z}, author+an = {2=me;1=student}, journal = {{Scientometrics}}, keywords = {Scientific uncertainty ; Semantic annotation ; Annotation framework ; Linguistic patterns}, month = may, publisher = {{Springer Verlag}}, year = {2024} }
Linguistic perspectives in deciphering citation function classification

Marc Bertin and Iana Atanassova

Jul 2024

Abs DOI Bib

Understanding citations within their context is a complex task in information science, critical for bibliometric analysis. The study of citation contexts and their types has been a central issue in recent work on citations. In this paper, we present an experiment on the semantic annotation of citation contexts using a rule-based approach. We processed articles from seven PLOS journals and performed semantic annotation of citation contexts based on linguistic resources we constructed. We built on previous work on verb form analysis, n-grams, and semantic category modeling in the form of a linguistic ontology. Based on our observations, we propose directions of work for the constitution of a semantically annotated corpora. The intermediate results obtained lead us to formulate hypotheses on the relation between the IMRaD structure and certain semantic categories. Furthermore, our results demonstrate the semantic richness of citation contexts and underscore the importance of access to full-text articles for ontology population in open science. The findings suggest that semantic categories vary across disciplines and rhetorical structures, necessitating further exploration with larger and more diverse datasets.
@article{Bertin2024, author = {Bertin, Marc and Atanassova, Iana}, journaltitle = {{Scientometrics}}, title = {{Linguistic perspectives in deciphering citation function classification}}, doi = {10.1007/s11192-024-05082-4}, url = {https://link.springer.com/article/10.1007/s11192-024-05082-4}, author+an = {2=me}, month = jul, publisher = {{Springer Verlag}}, year = {2024} }

Conference Papers

Approches linguistiques pour la fouille d’articles scientifiques

Iana Atanassova

In Atelier TextMine’24, Conférence internationale sur l’extraction et la gestion des connaissances (EGC 2024), Dijon, France, Jul 2024

Abs Bib

Dans cette présentation nous aborderons la problématique de la fouille de corpus scientifiques en différentes disciplines et en plein texte. Nous montrerons des résultats de l’annotation sémantique de corpus et l’extraction d’informations, par l’application d’approches fondées sur les ressources linguistiques qui seront mis en perspective avec des méthodes par apprentissage. Nous nous intéressons en particulier à la notion d’incertitude scientifique et à la possibilité de l’identifier et la catégoriser dans les textes des publications. Nous aborderons également la problématique du multilinguisme dans les articles à travers une étude de corpus.
@inproceedings{Atanassova2024, author = {Atanassova, Iana}, booktitle = {Atelier TextMine'24, Conf{\'e}rence internationale sur l'extraction et la gestion des connaissances (EGC 2024)}, year = {2024}, title = {Approches linguistiques pour la fouille d'articles scientifiques}, location = {Dijon, France}, author+an = {1=me}, }
Breaking Boundaries in Citation Parsing: A Comparative Study of Generative LLMs and Traditional Out-of-the-box Citation Parsers

Iana Atanassova and Marc Bertin

In International Workshop on Bibliometric-enhanced Information Retrieval (BIR 2024) co-located with the 46^st European Conference on Information Retrieval (ECIR 2024), Glasgow, Scotland, Jul 2024

Abs Bib

The task of citation string parsing has been the focus of many efforts. Traditional tools explicitly designed to parse bibliographic information, such as Bilbo, Grobid, and Parscit, have long been established in the academic landscape. Recently, with the emergence of general conversational LLMs (Large Language Models) such as OpenAI’s ChatGPT and Llama, an interesting question arises: can such language models, originally developed for natural language understanding (NLU), be employed to efficiently process bibliographies, and how would their performance for this task compare to that of dedicated bibliographic parsing tools? In this article, we propose an experiment to measure the ability of LLMs to analyse citation strings in different citation styles. We use a synthetic dataset with 12 different citation styles. We evaluate the output of two generative LLMs, ChatGPT 3.5 and Llama 2 7B, and two out-of-the-box citation parsers, CERMINE and Neural ParsCit. The results show that the LLMs tend to outperform the citation parsers for all citation styles and labels.
@inproceedings{Atanassova2024a, author = {Atanassova, Iana and Bertin, Marc}, booktitle = {{International Workshop on Bibliometric-enhanced Information Retrieval (BIR 2024) co-located with the 46st European Conference on Information Retrieval (ECIR 2024)}}, year = {2024}, title = {{Breaking Boundaries in Citation Parsing: A Comparative Study of Generative LLMs and Traditional Out-of-the-box Citation Parsers}}, location = {Glasgow, Scotland}, author+an = {1=me}, url = {https://ceur-ws.org/Vol-3989/paper-04.pdf}, }
Correction automatique de réponses textuelles : une approche basée sur des schémas conceptuels

Emel Dalgic, Alexandre Lefort, and Iana Atanassova

In Conférence internationale sur l’extraction et la gestion des connaissances (EGC 2024), Jan 2024

Abs Bib

Dans cet article, nous proposons une méthode pour la correction automatique de définitions produites par les étudiants dans le domaine de la gestion et l’économie. Notre algorithme traite les réponses textuelles des étudiants afin d’y identifier les concepts et relations correctement restituées et ceux qui sont erronés ou manquants. Nous avons effectué une évaluation sur plusieurs corpus de définitions, et les résultats montrent un score de F1 d’autour de 0,91 pour l’identification des relations, et des scores entre 0,75 et 0,83 pour l’identification des groupes nominaux arguments des relations. Cette approche s’inscrit dans un projet plus vaste autour de la correction automatique des réponses textuelles et la production d’outils destinés aux enseignants et apprenants.
@inproceedings{Dalgic2024, author = {Dalgic, Emel and Lefort, Alexandre and Atanassova, Iana}, booktitle = {Conf{\'e}rence internationale sur l'extraction et la gestion des connaissances (EGC 2024)}, title = {Correction automatique de réponses textuelles : une approche basée sur des schémas conceptuels}, address = {Dijon}, author+an = {3=me;1=student}, month = jan, year = {2024} }
CriticalMinds: Enhancing ML Models for ESG Impact Analysis Categorisation Using Linguistic Resources and Aspect-Based Sentiment Analysis

Iana Atanassova, Marine Potier, Maya Mathie, Marc Bertin, and Panggih Kusuma Ningrum

In Joint Workshop of the 7th Financial Technology and Natural Language Processing and the 5th Knowledge Discovery from Unstructured Data in Financial Services, and the 4th Workshop on Economics and Natural Language Processing @ LREC-COLING-2024, May 2024

Abs Bib PDF

This paper presents our method and findings for the ML-ESG-3 shared task for categorising Environmental, Social, and Governance (ESG) impact level and duration. We introduce a comprehensive machine learning framework incorporating linguistic and semantic features to predict ESG impact levels and durations in English and French. Our methodology uses features that are derived from FastText embeddings, TF-IDF vectors, manually crafted linguistic resources, the ESG taxonomy, and aspect-based sentiment analysis (ABSA). We detail our approach, feature engineering process, model selection via grid search, and results. The best performance for this task was achieved by the Random Forest and XGBoost classifiers, with micro-F1 scores of 47.06% and 65.44% for English Impact level and Impact length, and 39.04% and 54.79% for French Impact level and Impact length respectively.
@inproceedings{Atanassova2024b, author = {Atanassova, Iana and Potier, Marine and Mathie, Maya and Bertin, Marc and Ningrum, Panggih Kusuma}, booktitle = {{Joint Workshop of the 7th Financial Technology and Natural Language Processing and the 5th Knowledge Discovery from Unstructured Data in Financial Services, and the 4th Workshop on Economics and Natural Language Processing @ LREC-COLING-2024}}, title = {{CriticalMinds: Enhancing ML Models for ESG Impact Analysis Categorisation Using Linguistic Resources and Aspect-Based Sentiment Analysis}}, editor = {for Computational Linguistics, Association}, pages = {248--253}, series = {Financial Technology and Natural Language Processing (FinNLP)}, address = {Torino, Italy}, author+an = {1=me;2=student;3=student;5=student}, keywords = {ABSA ; ESG ; Impact level ; Impact length ; ESG taxonomy ; linguistic resources}, month = may, year = {2024} }
Le multilinguisme dans les références bibliographiques : une étude de corpus

Marc Bertin and Iana Atanassova

In Conférence internationale sur l’extraction et la gestion des connaissances (EGC 2024), Dijon, Jan 2024

Abs Bib

Le statut de lingua franca de l’anglais dans la recherche est déjà bien établi. Dans quelle mesure les citations d’articles rédigés en anglais sont-elles prédominantes par rapport aux articles rédigés dans d’autres langues ? Dans cet article, nous abordons le problème du multilinguisme dans les publications par l’analyse de deux corpus différents : d’un côté le Semantic Scholar Open Research Corpus, et d’un autre côté la base de données multilingue ISTEX. Notre objectif est d’examiner les références en langues étrangères (différentes de la langue de publication) dans ces corpus, et d’observer leur nature et leur distribution.
@inproceedings{Bertin2024b, author = {Bertin, Marc and Atanassova, Iana}, booktitle = {Conf{\'e}rence internationale sur l'extraction et la gestion des connaissances (EGC 2024)}, title = {Le multilinguisme dans les références bibliographiques : une étude de corpus}, location = {Dijon}, author+an = {2=me}, month = jan, year = {2024} }

Navigating the Unknown: A Textual Analysis of Uncertainty in Astrobiology Research

Christophe Malaterre, Iana Atanassova, Francis Lareau, and Panggih Kusuma Ningrum

In Congress of the Canadian Society for the History and Philosophy of Science (CSHPS), Jan 2024

Bib

@inproceedings{Malaterre2024,
  author = {Malaterre, Christophe and Atanassova, Iana and Lareau, Francis and Kusuma Ningrum, Panggih},
  booktitle = {{Congress of the Canadian Society for the History and Philosophy of Science (CSHPS)}},
  title = {{Navigating the Unknown: A Textual Analysis of Uncertainty in Astrobiology Research}},
  organization = {{Canadian Society for the History and Philosophy of Science (CSHPS)}},
  url = {https://hal.science/hal-04780332},
  address = {Montr{\'e}al (Qu{\'e}bec), Canada},
  author+an = {2=me;4=student},
  year = {2024}
}

Datasets

Annotated Dataset for Uncertainty Mining : Gold Standard

Nicolas Gutehrlé, Panggih Kusuma Ningrum, and Iana Atanassova

Nov 2024

DOI Bib

@dataset{Gutehrle2024,
  author = {Gutehrlé, Nicolas and Ningrum, Panggih Kusuma and Atanassova, Iana},
  title = {{Annotated Dataset for Uncertainty Mining : Gold Standard}},
  doi = {10.5281/zenodo.14134215},
  url = {https://doi.org/10.5281/zenodo.14134215},
  author+an = {3=me;1=student;2=student},
  month = nov,
  publisher = {Zenodo},
  year = {2024},
}

Synthetic Dataset of Citation Strings in 12 Styles

Marc Bertin and Iana Atanassova

Mar 2024

DOI Bib

@dataset{Bertin2024a,
  author = {Bertin, Marc and Atanassova, Iana},
  title = {Synthetic Dataset of Citation Strings in 12 Styles},
  doi = {10.5281/zenodo.10839503},
  url = {https://doi.org/10.5281/zenodo.10839503},
  version = {1.0.0},
  author+an = {2=me},
  month = mar,
  publisher = {Zenodo},
  year = {2024}
}

Technical Reports

Report on the Collab-a-thon at ECIR 2024

Sean Macavaney, Adam Roegiest, Aldo Lipani, Andrew Parry, Björn Engelmann, and 25 more authors

Mar 2024

Abs Bib PDF

We present a report on the Collab-a-thon, a series of sessions at the European Conference on Information Retrieval (ECIR) 2024 designed to help foster new collaborations during a conference. This report presents the motivation and design of the Collab-a-thon, a summary of the discussions covered at each session, and a set of recommendations for conducting similar events in the future. The event is set to run again at ECIR 2025 and planning is underway to pilot the event in a different community at the IEEE International Conference on Distributed Computing Systems (ICDCS) 2025.

@techreport{Macavaney2024,
  author = {Macavaney, Sean and Roegiest, Adam and Lipani, Aldo and Parry, Andrew and Engelmann, Bj{\"o}rn and Katharina, Christin and Meng, Chuan and Frayling, Erlend and Yang, Eugene and Schlatt, Ferdinand and Faggioli, Guglielmo and Scells, Harrisen and Atanassova, Iana and Friese, Jana and Bevendorff, Janek and Sanz-Cruzado, Javier and Trippas, Johanne and Pathak, Kanaad and Dhole, Kaustubh and Azzopardi, Leif and Fr{\"o}be, Maik and Bertin, Marc and Prasad, Nishchal and Zerhoudi, Saber and Wang, Shuai and Chatterjee, Shubham and Jaenich, Thomas and Kruschwitz, Udo and Wang, Xi and Long, Zijun},
  institution = {{ACM SIGIR Forum}},
  title = {{Report on the Collab-a-thon at ECIR 2024}},
  number = {1},
  url = {https://hal.science/hal-04746200},
  author+an = {13=me},
  month = mar,
  volumne = {58},
  year = {2024}
}

2023

Conference Papers

A journey into Scientific Uncertainty: Building a Project of Excellence in the HSS

Iana Atanassova

In Networking and Training Workshop - CrECI Project, Mar 2023
Citing Foreign Language Sources: an Analysis of the S2ORC Dataset

Marc Bertin and Iana Atanassova

In 10^th International Workshop on Bibliometric-enhanced Information Retrieval (BIR 2023) co-located with the European Conference on Information Retrieval (ECIR 2023), Mar 2023

Abs Bib

In this article we investigate the multilingualism of references in the Semantic Scholar Open Research Corpus (S2ORC). While this dataset contains peer-reviewed papers from different disciplines, written mainly in English, we identify the languages used in the references, their linguistic groups and their distribution over time. The results allow us to observe the dominance of English in science, as well as the relative proportions of the other 34 languages, representing over 2.4 million of the cited sources, and their linguistic groups. We show that the relative share of non-English citations has been increasing since 2000. However, the vast majority of citations in non-English publications are to English sources. We discuss some of the limitations of this study, mainly related to the nature of the dataset, which is biased towards English, and the quality of the language detection tool.
@inproceedings{Bertin2023a, author = {Bertin, Marc and Atanassova, Iana}, title = {{Citing Foreign Language Sources: an Analysis of the S2ORC Dataset}}, booktitle = {{10th International Workshop on Bibliometric-enhanced Information Retrieval (BIR 2023) co-located with the European Conference on Information Retrieval (ECIR 2023)}}, year = {2023}, address = {Dublin, Ireland}, author+an = {2=me}, }
Comprendre les archives : vers de nouvelles interfaces de recherche reposant sur l’annotation sémantique des documents

Nicolas Gutehrlé and Iana Atanassova

In CiDE.23 : 23ème édition du Colloque International sur le Document Electronique "Document et archivage : pratiques formelles et informelles dans les organisations", Mar 2023

Abs Bib

Les campagnes de numérisation menées ces dernières années par les bibliothèques et archives ont facilité l’accès aux documents de leurs collections. Cependant, explorer et exploiter ces contenus restent des tâches difficiles en raison de la quantité de documents consultables. Dans cet article, nous montrons comment l’annotation sémantique du contenu textuel de corpus d’études issus de documents d’archives permet d’en faciliter l’exploitation et la valorisation. Nous présentons d’abord un cadre méthodologique pour la construction de nouvelles interfaces qui reposent sur la sémantique textuelle, puis abordons les verrous technologiques actuels, et leurs potentielles solutions. Nous terminons par la présentation d’un cas pratique de l’application de ce cadre.
@inproceedings{Gutehrle2023, author = {Gutehrlé, Nicolas and Atanassova, Iana}, booktitle = {{CiDE.23 : 23ème édition du Colloque International sur le Document Electronique "Document et archivage : pratiques formelles et informelles dans les organisations"}}, title = {{Comprendre les archives : vers de nouvelles interfaces de recherche reposant sur l'annotation sémantique des documents}}, address = {Grenoble, France}, author+an = {2=me;1=student}, year = {2023} }
Contextual Analysis of Citations in Context Using Rule-Based Approaches. Best Soups are Made in Old Pots

Marc Bertin and Iana Atanassova

In 19^th International Conference of the International Society for Scientometrics and Informetrics (ISSI 2023), Jul 2023

Abs Bib

In this paper, we present an experiment on annotating citation contexts using a rule-based approach to investigate the extent of text around citations. The study of citation contexts and their types has been a central issue in recent work on citations. We processed articles from seven PLOS journals and performed semantic annotation of citation contexts based on linguistic resources we constructed. We built on previous work on verb form analysis, n-grams, and semantic category modeling in the form of a linguistic ontology. Based on the observations obtained, we propose some directions of work for the constitution of a semantically annotated corpus. The intermediate results obtained lead us to formulate hypotheses between the IMRaD structure and certain semantic categories.
@inproceedings{Bertin2023, author = {Bertin, Marc and Atanassova, Iana}, booktitle = {19th International Conference of the International Society for Scientometrics and Informetrics (ISSI 2023)}, title = {Contextual Analysis of Citations in Context Using Rule-Based Approaches. Best Soups are Made in Old Pots}, address = {Bloomington, Indiana, US}, author+an = {2=me}, month = jul, year = {2023}, }
Multilinguism in References: a study of the ISTEX Dataset

Iana Atanassova and Marc Bertin

In 19^th International Conference of the International Society for Scientometrics and Informetrics (ISSI 2023), Jul 2023

Abs Bib

The lingua franca status of English in research is already well established. Rao (2019), for example, highlights the importance of English as a world language and shows how widely it is used in scientific research, business and education. In this paper, we propose to investigate the extent to which the language of an article determines the languages of the papers that are cited, and whether citations to papers written in different languages are distributed in the same way as papers published in those languages. In other words: To what extent are citations to articles written in English predominant in articles written in other languages?
@inproceedings{Atanassova2023, author = {Atanassova, Iana and Bertin, Marc}, booktitle = {19th International Conference of the International Society for Scientometrics and Informetrics (ISSI 2023)}, title = {{Multilinguism in References: a study of the ISTEX Dataset}}, address = {Bloomington, Indiana, US}, author+an = {1=me}, month = jul, year = {2023}, }
Scientific Uncertainty: an Annotation Framework and Corpus Study in Different Disciplines

Panggih Kusuma Ningrum and Iana Atanassova

In 19^th International Conference of the International Society for Scientometrics and Informetrics (ISSI 2023), Jul 2023

Abs Bib

Scientific uncertainty is an integral part of the research process and inherent to the construction of new knowledge. In this paper, we investigate the ways in which uncertainty is expressed in articles and propose a new interdisciplinary annotation framework to categories sentences containing uncertainty along five dimensions. We study a corpus of articles from different disciplines and conduct experiments on two different samples of sentences: one sample extracted by uncertainty cue mapping and another sample obtained from manual annotation of randomly selected articles. The two samples are manually annotated using our annotation framework. The results show the distribution of uncertainty types across journals and categories. The samples of annotated sentences can also be used to automate some aspects of the annotation process.
@inproceedings{Ningrum2023, author = {Ningrum, Panggih Kusuma and Atanassova, Iana}, booktitle = {19th International Conference of the International Society for Scientometrics and Informetrics (ISSI 2023)}, title = {{Scientific Uncertainty: an Annotation Framework and Corpus Study in Different Disciplines}}, address = {Bloomington, Indiana, US}, author+an = {2=me;1=student}, month = jul, year = {2023}, }
UnScientify: Detecting Scientific Uncertainty in Scholarly

Panggih Kusuma Ningrum, Philipp Mayr, and Iana Atanassova

In Proceedings of Joint Workshop of the 4th Extraction and Evaluation of Knowledge Entities from Scientific Documents (EEKE2023) and the 3rd AI + Informetrics (AII2023) co-located with the JCDL 2023, Jun 2023

Abs Bib

This demo paper presents UnScientify (https://bit.ly/unscientify-demo), an interactive system designed to detect scientific uncertainty in scholarly full text. The system utilizes a weakly supervised technique that employs a fine-grained annotation scheme to identify verbally formulated uncertainty at the sentence level in scientific texts. The pipeline for the system includes a combination of pattern matching, complex sentence checking, and authorial reference checking. Our approach automates labeling and annotation tasks for scientific uncertainty identification, taking into account different types of scientific uncertainty, that can serve various applications such as information retrieval, text mining, and scholarly document processing. Additionally, UnScientify provides interpretable results, aiding in the comprehension of identified instances of scientific uncertainty in text.
@inproceedings{Ningrum2023a, author = {Ningrum, Panggih Kusuma and Mayr, Philipp and Atanassova, Iana}, booktitle = {Proceedings of Joint Workshop of the 4th Extraction and Evaluation of Knowledge Entities from Scientific Documents (EEKE2023) and the 3rd AI + Informetrics (AII2023) co-located with the JCDL 2023}, title = {UnScientify: Detecting Scientific Uncertainty in Scholarly}, address = {Santa Fe, New Mexico, USA and Online}, author+an = {3=me;1=student}, month = jun, year = {2023} }

Datasets

Dataset for Multidisciplinary Uncertainty Mining - ver1

Panggih Kusuma Ningrum and Iana Atanassova

Jun 2023

DOI Bib

@dataset{Ningrum2023b,
  author = {Ningrum, Panggih Kusuma and Atanassova, Iana},
  title = {{Dataset for Multidisciplinary Uncertainty Mining - ver1}},
  doi = {10.5281/zenodo.8024787},
  url = {https://doi.org/10.5281/zenodo.8024787},
  version = {1},
  author+an = {2=me;1=student},
  month = jun,
  publisher = {Zenodo},
  year = {2023},
}

Questions for Galops 1-7 horse riding theoretical exams and their textual answers with enumerations

Marine Potier and Iana Atanassova

Dec 2023

DOI Bib

@dataset{Potier2023,
  author = {Potier, Marine and Atanassova, Iana},
  title = {{Questions for Galops 1-7 horse riding theoretical exams and their textual answers with enumerations}},
  doi = {10.5281/zenodo.10303742},
  url = {https://doi.org/10.5281/zenodo.10303742},
  author+an = {2=me;1=student},
  month = dec,
  publisher = {Zenodo},
  year = {2023},
}

TimeTank: A Corpus of Sentences Annotated with TimeInfo for Temporal Data

Salah Yahiaoui and Iana Atanassova

Sep 2023

DOI Bib

@dataset{Yahiaoui2023,
  author = {Yahiaoui, Salah and Atanassova, Iana},
  title = {{TimeTank: A Corpus of Sentences Annotated with TimeInfo for Temporal Data}},
  doi = {10.5281/zenodo.8364409},
  url = {https://doi.org/10.5281/zenodo.8364409},
  version = {1.0},
  author+an = {2=me;1=student},
  month = sep,
  publisher = {Zenodo},
  year = {2023},
}

2022

Journal Articles

Editorial: Mining Scientific Papers, Volume II: Knowledge Discovery and Data Exploitation

Iana Atanassova, Marc Bertin, and Philipp Mayr

Frontiers in Research Metrics and Analytics, Sep 2022

DOI Bib

@article{Atanassova2022a,
  author = {Atanassova, Iana and Bertin, Marc and Mayr, Philipp},
  title = {Editorial: Mining Scientific Papers, Volume II: Knowledge Discovery and Data Exploitation},
  doi = {10.3389/frma.2022.911070},
  editor = {Chen, Chaomei},
  issn = {2504-0537},
  url = {https://www.frontiersin.org/articles/10.3389/frma.2022.911070},
  volume = {7},
  journal = {Frontiers in Research Metrics and Analytics},
  keywords = {Data mining ; Text Mining ; Semantic publishing ; Scientific papers ; Bibliometrics ; Scientometrics ; Natural Language Processing ; Computational Linguistics ; Citation Content Analysis ; Academic Search},
  year = {2022},
  author+an = {1=me},
}

Noyau Informatique CripTex pour le Traitement de Données Personelles dans les Textes

Abdoulaye Guisse and Iana Atanassova

BULAG, Sep 2022

Abs Bib

Nous présentons dans cet article une approche pour l’identification et la catégorisation des données personnelles dans les textes, basée sur la théorie micro-systémique proposée par S. Cardey, et une implémentation d’un noyau informatique qui peut être intégré dans des applications tierces. Cette recherche répond aux besoins d’entreprises de pouvoir identifier et gérer les données personnelles dans les textes, suite à l’adoption du réglement RGPD. Nous détaillons l’approche linguistique pour l’identification des données personnelles, ainsi que l’implémentation informatique de l’outil CripTex avec son API REST et interface web. La recherche présentée dans cet article a été financée en partie par le Projet Interreg France-Suisse DecRIPT (2020-2022).
@article{Guisse2022, author = {Guisse, Abdoulaye and Atanassova, Iana}, title = {{Noyau Informatique CripTex pour le Traitement de Données Personelles dans les Textes}}, journal = {BULAG}, journaltitle = {Bulletin de Linguistique Appliquée et Générale, Presses Universitaires de Franche-Comté PUFC}, editor = {Cardey, Sylviane and Rey, François-C and Atanassova, Iana}, volume = {40}, pages = {597--612}, issn = {0758 6787}, author+an = {2=me;1=student}, year = {2022} }
Preprint Citation Pratice in PLOS

Marc Bertin and Iana Atanassova

Scientometrics, Sep 2022

Abs DOI Bib

The role of preprints in the scientific production and their part in citations have been growing over the past 10 years. In this paper we study preprint citations in several different aspects: the progression of preprint citations over time, their relative frequencies in relation to the IMRaD structure of articles, their distributions over time, per preprint database and per PLOS journal. We have processed the PLOS corpus that covers 7 journals and a total of about 240,000 articles up to January 2021, and produced a dataset of 8,460 preprint citation contexts that cite 12 different preprint databases. Our results show that preprint citations are found with the highest frequency in the Method section of articles, though small variations exist with respect to journals. The PLOS Computational Biology journal stands out as it contains more than three times more preprint citations than any other PLOS journal. The relative parts of the different preprint databases are also examined. While ArXiv and bioRxiv are the most frequent citation sources, bioRxiv’s disciplinary nature can be observed as it is the source of more than 70% of preprint citations in PLOS Biology, PLOS Genetics and PLOS Pathogens. We have also compared the lexical content of preprint citation contexts to the citation content to peer-reviewed publications. Finally, by performing a lexicometric analysis, we have shown that preprint citation contexts differ significantly from citation contexts of peer-reviewed publications. This confirms that authors make use of different lexical content when citing preprints compared to the rest of citations.
@article{Bertin2022, author = {Bertin, Marc and Atanassova, Iana}, title = {{Preprint Citation Pratice in PLOS}}, doi = {10.1007/s11192-022-04388-5}, number = {12}, pages = {6895--6912}, url = {https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9186004/}, volume = {127}, journal = {Scientometrics}, keywords = {Preprint ; Citation contexts ; Bibliometrics ; IMRaD ; Correspondence Analysis ; PLOS}, year = {2022}, author+an = {2=me}, }
Processing the structure of documents: Logical Layout Analysis of historical newspapers in French

Nicolas Gutehrlé and Iana Atanassova

Journal of Data Mining & Digital Humanities, May 2022

Abs DOI Bib

Background. In recent years, libraries and archives led important digitisation campaigns that opened the access to vast collections of historical documents. While such documents are often available as XML ALTO documents, they lack information about their logical structure. In this paper, we address the problem of Logical Layout Analysis applied to historical documents in French. We propose a rule-based method, that we evaluate and compare with two Machine-Learning models, namely RIPPER and Gradient Boosting. Our data set contains French newspapers, periodicals and magazines, published in the first half of the twentieth century in the Franche-Comté Region. Results. Our rule-based system outperforms the two other models in nearly all evaluations. It has especially better Recall results, indicating that our system covers more types of every logical label than the other two models. When comparing RIPPER with Gradient Boosting, we can observe that Gradient Boosting has better Precision scores but RIPPER has better Recall scores. Conclusions. The evaluation shows that our system outperforms the two Machine Learning models, and provides significantly higher Recall. It also confirms that our system can be used to produce annotated data sets that are large enough to envisage Machine Learning or Deep Learning approaches for the task of Logical Layout Analysis. Combining rules and Machine Learning models into hybrid systems could potentially provide even better performances. Furthermore, as the layout in historical documents evolves rapidly, one possible solution to overcome this problem would be to apply Rule Learning algorithms to bootstrap rule sets adapted to different publication periods.
@article{Gutehrle2022, author = {Gutehrlé, Nicolas and Atanassova, Iana}, title = {{Processing the structure of documents: Logical Layout Analysis of historical newspapers in French}}, doi = {10.46298/jdmdh.9093}, url = {https://jdmdh.episciences.org/9614}, volume = {{NLP4DH}}, author+an = {2=me;1=student}, journal = {{Journal of Data Mining \& Digital Humanities}}, keywords = {Logical Layout Analysis, Historical Newspapers, Natural Language Processing, Rule-based system, Rule-Learning, Machine-Learning}, month = may, year = {2022} }

Conference Papers

Personal Data in Texts: Detection, Annotation and Governance

Iana Atanassova, Thierry Bregnard, Walid El Abed, Hitoshi Isahara, and Sylviane Cardey

In Panel in Computers, Privacy and Data Protection (CPDP) Conference, May 2022

Bib

@inproceedings{Atanassova2022,
  author = {Atanassova, Iana and Bregnard, Thierry and Abed, Walid El and Isahara, Hitoshi and Cardey, Sylviane},
  booktitle = {Panel in Computers, Privacy and Data Protection (CPDP) Conference},
  title = {Personal Data in Texts: Detection, Annotation and Governance},
  url = {https://www.youtube.com/watch?v=3oYv4cMWhvY},
  venue = {Brussels, Belgium},
  author+an = {1=me},
  year = {2022}
}

Semantically-Driven Knowledge Modelling for the Business Ecosystem

Walid El Abed, Hélène Madinier, Sylviane Cardey, Thierry Bregnard, and Iana Atanassova

In International Forum on Knowledge Asset Dynamics - IFKAD, Managing Knowledge for Sustainability, May 2022

Abs Bib

The digital world and its complex interactions create new challenges for the Digital Enterprise. The knowledge required for human activity in the value creation is fragmented and dispersed across systems which in their turn are not normalized, siloed and inconsistent. The disconnection of the knowledge and business context render the results obsolete, due to the high pace of changes in our societies and behaviours. In this paper we present a general framework to enable knowledge modelling that relies on the semantics of natural language in order to ensure sustainable data governance for the entire business ecosystem. Our proposal based on the Data Excellence Science is to provide a new vision, method and mechanics for knowledge modelling that enables semantic driven communication between humans and machines.
@inproceedings{ElAbed2022, author = {El Abed, Walid and Madinier, Hélène and Cardey, Sylviane and Bregnard, Thierry and Atanassova, Iana}, booktitle = {International Forum on Knowledge Asset Dynamics - IFKAD, Managing Knowledge for Sustainability}, title = {Semantically-Driven Knowledge Modelling for the Business Ecosystem}, venue = {Lugano, Switzerlard}, author+an = {5=me}, year = {2022} }
TimeInfo : a Semantic Annotation Framework for Temporal Information in Scientific Papers

Salah Yahiaoui and Iana Atanassova

In Terminology & Ontology: Théories and applications (TOTh 2022), May 2022

Abs Bib

In this article we propose a new schema for the annotation of temporal expressions in texts that we name TimeInfo. Also, we present and analyse existing models for temporal data annotation. Then, we define the set of elements and their attributes in TimeInfo and explain how these elements provide finer distinctions for the annotation of temporal expressions. The main purpose of our model is to allow for better detection, extraction, and semantic representation of temporal data in scientific papers. Finally, we present the use cases and the different applications that can be developed using the TimeInfo framework.
@inproceedings{Yahiaoui2022, author = {Yahiaoui, Salah and Atanassova, Iana}, title = {{TimeInfo : a Semantic Annotation Framework for Temporal Information in Scientific Papers}}, booktitle = {{Terminology \& Ontology: Th\'eories and applications (TOTh 2022)}}, author+an = {2=me;1=student}, year = {2022} }

Special Issues

Languages Analysis, Comparison and Generation - Systems, Models and Applications

Sylviane Cardey-Greenfield, François-Claude Rey, and Iana Atanassova

In BULAG - Bulletin de linguistique appliquée et générale, May 2022

Bib

@incollection{CardeyGreenfield2022,
  author = {Cardey-Greenfield, Sylviane and Rey, Fran{\c c}ois-Claude and Atanassova, Iana},
  booktitle = {BULAG - Bulletin de linguistique appliquée et générale},
  title = {{Languages Analysis, Comparison and Generation - Systems, Models and Applications}},
  number = {40},
  publisher = {{Presses Universitaires de Franche-Comt{\'e}}},
  author+an = {3=me;2=student},
  issn = {0758-6787},
  year = {2022}
}

Mining Scientific Papers Volume II: Knowledge Discovery and Data Exploitation

In Frontiers in Research Metrics and Analytics, May 2022

Bib

@incollection{Atanassova2022b,
  booktitle = {Frontiers in Research Metrics and Analytics},
  title = {Mining Scientific Papers Volume II: Knowledge Discovery and Data Exploitation},
  editor = {Atanassova, Iana and Bertin, Marc and Mayr, Philipp},
  url = {https://www.frontiersin.org/research-topics/13388/mining-scientific-papers-volume-ii-knowledge-discovery-and-data-exploitation},
  year = {2022},
  editor+an = {1=me},
}

2021

Journal Articles

Indirectly Named Entity Recognition

Alexis Kauffmann, François-Claude Rey, Iana Atanassova, Arnaud Gaudinat, Peter Greenfield, and 2 more authors

Journal of Computer-Assisted Linguistic Research (JCLR), May 2021

Abs DOI Bib

We define here indirectly named entities, as a term to denote multiword expressions referring to known named entities by means of periphrasis. While named entity recognition is a classical task in natural language processing, little attention has been paid to indirectly named entities and their treatment. In this paper, we try to address this gap, describing issues related to the detection and understanding of indirectly named entities in texts. We introduce a proof of concept for retrieving both lexicalised and non-lexicalised indirectly named entities in French texts. We also show example cases where this proof of concept is applied, and discuss future perspectives. We have initiated the creation of a first lexicon of 712 indirectly named entity entries that is available for future research.
@article{Kauffmann2021, author = {Kauffmann, Alexis and Rey, Fran{\c c}ois-Claude and Atanassova, Iana and Gaudinat, Arnaud and Greenfield, Peter and Madinier, H{\'e}l{\`e}ne and Cardey, Sylviane}, title = {{Indirectly Named Entity Recognition}}, doi = {10.4995/JCLR.2021.15922}, number = {1}, pages = {27--46}, url = {https://polipapers.upv.es/index.php/jclr/article/view/15922}, volume = {5}, author+an = {3=me;2=student}, journal = {{Journal of Computer-Assisted Linguistic Research (JCLR)}}, keywords = {named entities ; indirectly named entities ; information extraction ; named entity recognition ; multiword expressions ; text processing ; text mining}, publisher = {{Universitat Polit{\`e}cnica de Val{\`e}ncia}}, year = {2021} }

Conference Papers

Data Papers et dissémination des données de la recherche : quelles pratiques en SHS ?

Mariannig Le Béchec and Iana Atanassova

In Colloque DHNord2021 : Publier, partager, réutiliser les données de la recherche : les data papers et leurs enjeux, Nov 2021

Abs Bib

Les data papers s’intègrent comme un élément indispensable de l’écosystème de la Science Ouverte. Notre objectif est de répondre aux questions suivantes : quelles sont les différences disciplinaires qui existent quant à l’appropriation des data papers par les chercheurs ? Quelle est la place des data papers en tant qu’outil de dissémination des données de la recherche dans les SHS ? Notre proposition s’appuie sur l’analyse de trois corpus pour décrire les pratiques autour des data papers et de la dissémination des données en SHS à différentes échelles : les données sur un panel de participants aux formations courtes dispensées sur la rédaction et la publication de data papers en France ; les réponses de 1089 membres des communautés scientifiques en France à un questionnaire diffusé en ligne en 2020 ; et les métadonnées de 10 000 jeux de données et 10 000 publications disponibles sur l’entrepôt généraliste Zenodo. Les résultats de notre étude montrent que la publication de data papers et l’usage des entrepôts en SHS ne sont pas encore des pratiques établies mais émergentes pour la dissémination des données de la recherche.
@inproceedings{LeBechec2021, author = {Le B{\'e}chec, Mariannig and Atanassova, Iana}, booktitle = {{Colloque DHNord2021 : Publier, partager, réutiliser les données de la recherche : les data papers et leurs enjeux}}, title = {{Data Papers et diss{\'e}mination des donn{\'e}es de la recherche : quelles pratiques en SHS~?}}, address = {France}, author+an = {2=me}, month = nov, year = {2021} }
Enjeux de l’étude des contextes citationnels dans le cadre des études bibliométriques : contextes de citation et blocs citationnels

Marc Bertin and Iana Atanassova

In CiDE.22 : 22éme édition du Colloque International sur le Document Electronique Données Documents Connaissances : Perspectives de recherche et d’enseignement, Paris, France, Nov 2021

Abs Bib

La compréhension des actes de citation est une étape nécessaire à la catégorisation des relations sémantiques entre les oeuvres. Le traitement des phénomènes sémantico-pragmatiques tels que l’anaphore, la cataphore et la deixis est central dans l’analyse et la catégorisation des actes de citation. Dans cet articles que nous avons proposé une définition de bloc de citation, afin de poser la base d’une réflexion autour de la taille des segments textuels qui doivent être considérés pour les analyses automatisées des contextes de citation. Nous avons mené une première expérimentation afin de déterminer les tailles des blocs de citation dans différentes sections de la structure IMRaD des articles.
@inproceedings{Bertin2021, author = {Bertin, Marc and Atanassova, Iana}, booktitle = {{CiDE.22 : 22{\'e}me {\'e}dition du Colloque International sur le Document Electronique Donn{\'e}es Documents Connaissances : Perspectives de recherche et d'enseignement}}, title = {{Enjeux de l'{\'e}tude des contextes citationnels dans le cadre des {\'e}tudes bibliom{\'e}triques : contextes de citation et blocs citationnels}}, location = {Paris, France}, author+an = {2=me}, year = {2021} }
Identification et gestion des données personnelles dans les textes

Iana Atanassova, Sylviane Cardey-Greenfield, Hélène Madinier, and Walid El Abed

In CiDE.22 : 22éme édition du Colloque International sur le Document Electronique Données Documents Connaissances : Perspectives de recherche et d’enseignement, Nov 2021

Abs Bib

La protection des données de valeur, comme celles relatives aux personnes, est aujourd’hui un enjeu majeur pour les entreprises. Nous proposons de traiter automatiquement la sémantique des textes en langage naturel en vue d’identifier les données des personnes pour leur sécurité, leur offuscation et leur gouvernance. Notre approche s’appuie sur une modélisation sémantique-linguistique qui permet d’assurer la traçabilité complète de l’analyse. La mise en cohérence (mapping) entre la sémantique des données textuelles et la sémantique des données structurées de l’entreprise rend possible la gouvernance des données textuelles. Nous présentons la méthodologie générale pour l’identification de données personnelles dans des textes, ainsi que les concepts qui ont été modélisés pour la gouvernance des données personnelles.
@inproceedings{Atanassova2021a, author = {Atanassova, Iana and Cardey-Greenfield, Sylviane and Madinier, H{\'e}l{\`e}ne and El Abed, Walid}, booktitle = {{CiDE.22 : 22{\'e}me {\'e}dition du Colloque International sur le Document Electronique Donn{\'e}es Documents Connaissances : Perspectives de recherche et d'enseignement}}, title = {{Identification et gestion des donn{\'e}es personnelles dans les textes}}, address = {Paris, France}, author+an = {1=me}, year = {2021} }

Logical Layout Analysis Applied to Historical Newspapers

Nicolas Gutehrlé and Iana Atanassova

In Workshop on Natural Language Processing for Digital Humanities (NLP4DH) co-located with ICON 2021, Dec 2021

Bib

@inproceedings{Gutehrle2021,
  author = {Gutehrl{\'e}, Nicolas and Atanassova, Iana},
  booktitle = {{Workshop on Natural Language Processing for Digital Humanities (NLP4DH) co-located with ICON 2021}},
  title = {{Logical Layout Analysis Applied to Historical Newspapers}},
  url = {https\://hal.archives-ouvertes.fr/hal-03468972/file/9_Paper-2.pdf},
  abstarct = {In recent years, libraries and archives led important digitisation campaigns that opened the access to vast collections of historical documents. While such documents are often available as XML ALTO documents, they lack information about their logical structure. In this paper, we address the problem of logical layout analysis applied to historical documents. We propose a method which is based on the study of a dataset in order to identify rules that assign logical labels to both block and lines of text from XML ALTO documents. Our dataset contains newspapers in French, published in the first half of the 20th century. The evaluation shows that our methodology performs well for the identification of first lines of paragraphs and text lines, with F1 above 0.9. The identification of titles obtains an F1 of 0.64. This method can be applied to preprocess XML ALTO documents in preparation for downstream tasks, and also to annotate largescale datasets to train machine learning and deep learning algorithms.},
  author+an = {2=me;1=student},
  month = dec,
  year = {2021}
}

The Place of Preprint Citations in the IMRaD Structure: a Study of PLOS Journals

Marc Bertin and Iana Atanassova

In 18^th International Conference of the International Society for Scientometrics and Informetrics (ISSI 2021), Leuven, Belgium, Dec 2021

Abs Bib

The role of preprints in the scientific production and their part in citations have been growing over the past 10 years. In this paper we propose to study the citations of preprints in several different aspects: the progression of these citations over time, the sections of the articles in which they are most likely to appear and the percentage of such citations with respect to all citations in articles. We have processed the PLOS dataset that covers 7 journals and a total of about 240000 articles up to January 2021. The results show that preprint citations are found with the highest frequency in the Method section of articles, though small variations exist with respect to journals. The PLOS Computational Biology journal stands out as it contains more than three times more preprint citations than any other PLOS journal. The relative parts of the different preprint databases are also examined. While ArXiv and bioRxiv are the most frequent citation sources, bioRxiv’s disciplinary nature can be observed as it is the source of more than 70% of preprint citations in PLOS Biology, PLOS Genetics and PLOS Pathogens.
@inproceedings{Bertin2021a, author = {Bertin, Marc and Atanassova, Iana}, booktitle = {18th International Conference of the International Society for Scientometrics and Informetrics (ISSI 2021)}, year = {2021}, title = {{The Place of Preprint Citations in the IMRaD Structure: a Study of PLOS Journals}}, location = {Leuven, Belgium}, author+an = {2=me}, }

Datasets

Dataset for Logical-layout analysis on French historical newspapers

Nicolas Gutehrlé and Iana Atanassova

Oct 2021

DOI Bib

@dataset{Gutehrle2021a,
  author = {Gutehrl{\'e}, Nicolas and Atanassova, Iana},
  title = {{Dataset for Logical-layout analysis on French historical newspapers}},
  doi = {10.5281/zenodo.5752440},
  url = {https://doi.org/10.5281/zenodo.5752440},
  version = {1.0},
  author+an = {2=me;1=student},
  month = oct,
  publisher = {Zenodo},
  year = {2021},
}

Miscellaneous

Categorising Scientific Uncertainty in Papers

Iana Atanassova and François-C. Rey

Oct 2021

Poster

Bib

@misc{Atanassova2021,
  author = {Atanassova, Iana and Rey, Fran{\c c}ois-C.},
  title = {{Categorising Scientific Uncertainty in Papers}},
  note = {Poster},
  organization = {{SciNLP 2021 at Virtual conference hosted at Automated Knowledge Base Construction (ABKC) 2021}},
  author+an = {1=me;2=student},
  keywords = {Epistemic uncertainty ; Incertitude Epist{\'e}mique ; Incertidumbre epistemol{\'o}gica ; Incertidumbre epist{\'e}mica},
  year = {2021}
}

2020

Conference Papers

Concevoir un dispositif innovant pour professionnaliser la formation au référencement web : le projet SEO-ELP

Jean-Claude Domenget, Sylvain Sagot, and Iana Atanassova

In Congrès ACFAS, Oct 2020

Bib

@inproceedings{Domenget2020,
  author = {Domenget, Jean-Claude and Sagot, Sylvain and Atanassova, Iana},
  title = {{Concevoir un dispositif innovant pour professionnaliser la formation au référencement web~: le projet SEO-ELP}},
  booktitle = {Congrès ACFAS},
  year = {2020},
  address = {Sherbrooke, Canada},
  author+an = {3=me},
}

2019

Journal Articles

Editorial: Mining Scientific Papers: NLP-enhanced Bibliometrics

Iana Atanassova, Marc Bertin, and Philipp Mayr

Frontiers in Research Metrics and Analytics, Oct 2019

DOI Bib

@article{Atanassova2019b,
  author = {Atanassova, Iana and Bertin, Marc and Mayr, Philipp},
  title = {Editorial: Mining Scientific Papers: NLP-enhanced Bibliometrics},
  doi = {10.3389/frma.2019.00002},
  editor = {Chen, Chaomei},
  issn = {2504-0537},
  pages = {2},
  volume = {4},
  journal = {Frontiers in Research Metrics and Analytics},
  keywords = {Data mining ; Text Mining ; Semantic publishing ; Scientific papers ; Bibliometrics ; Scientometrics ; Natural Language Processing ; Computational Linguistics ; Citation Content Analysis ; Academic Search},
  year = {2019},
  author+an = {1=me},
}

Sécuriser le traitement des traces numériques dans le cadre du Règlement général sur la protection des données (RGPD) : anonymisation et pseudonymisation

Iana Atanassova, Marc Bertin, and Mariannig Le Béchec

I2D – Information, données & documents, Oct 2019

Abs Bib

Depuis l’entrée en vigueur en mai 2018 du Règlement général sur la protection des données (RGPD), la protection des données personnelles est une obligation pour toutes les entreprises de l’Union européenne. Comment faire face à cet enjeu majeur, difficile à traiter ? Plusieurs mesures techniques sont prévues, en particulier l’anonymisation et la pseudonymisation.
@article{Atanassova2019d, author = {Atanassova, Iana and Bertin, Marc and Le Béchec, Mariannig}, title = {Sécuriser le traitement des traces numériques dans le cadre du Règlement général sur la protection des données (RGPD) : anonymisation et pseudonymisation}, issn = {2428-2111}, pages = {55--58}, journal = {I2D – Information, données \& documents}, year = {2019}, author+an = {1=me}, }

Conference Papers

A preliminary study to compare deep learning with rule-based approaches for citation classification

Julien Perier-Camby, Marc Bertin, Iana Atanassova, and Frédéric Armetta

In 8^th International Workshop on Bibliometric-enhanced Information Retrieval (BIR 2019) co-located with the 41^st European Conference on Information Retrieval (ECIR 2019), Apr 2019

Abs Bib

Categorization of semantic relationships between scientific papers is a key to characterize the condition of a research field and to identify influential works. Recently, new approaches based on Deep Learning have demonstrated good capacities to tackle Natural Language Processing problems, such as text classification and information extraction. In this paper, we show how deep learning algorithms can automatically learn to classify citations, and could provide a relevant alternative when compared with methods based on pattern extractions from the recent state of the art. The paper discusses their appropriateness given the requirement of large datasets to train neural networks.
@inproceedings{PerierCamby2019, author = {Perier-Camby, Julien and Bertin, Marc and Atanassova, Iana and Armetta, Fr{\'e}d{\'e}ric}, booktitle = {{8th International Workshop on Bibliometric-enhanced Information Retrieval (BIR 2019) co-located with the 41st European Conference on Information Retrieval (ECIR 2019)}}, title = {{A preliminary study to compare deep learning with rule-based approaches for citation classification}}, pages = {125--131}, volume = {2345}, address = {Cologne, Germany}, author+an = {3=me}, month = apr, year = {2019} }
Analyse morphosyntaxique de l’arabe par une approche linguistique

Youcef Ihab Morsi and Iana Atanassova

In Terminology & Ontology: Théories and applications (TOTh 2019), Jun 2019

Abs Bib

Nous proposons un outil d’analyse morphosyntaxique de l’arabe standard moderne qui est basé sur l’étude linguistique des schèmes. Notre premier objectif est de proposer des règles linguistiques pour l’analyse morphosyntaxique et évaluer notre méthode sur le corpus annoté Arabic-PADT UD Treebank. Ce dernier, destiné au développement d’outils par apprentissage automatique, comporte de nombreuses occurrences de mots annotés avec une étiquette X, signalant une classe inconnue. Le deuxième objectif de notre étude est de proposer une méthode pour améliorer cette ressource en annotant ces occurrences inconnues avec les classes adéquates. Ainsi notre méthode vise à optimiser ce corpus annoté. Les deux évaluations montrent une F-mesure de 0,92 et 0,90 pour les analyses morphosyntaxiques.
@inproceedings{Morsi2019, author = {Morsi, Youcef Ihab and Atanassova, Iana}, booktitle = {{Terminology \& Ontology: Th\'eories and applications (TOTh 2019)}}, title = {{Analyse morphosyntaxique de l'arabe par une approche linguistique}}, address = {Chamb{\'e}ry, France}, author+an = {2=me;1=student}, month = jun, year = {2019} }

Beyond Metadata: the New Challenges in Mining Scientific Papers (Keynote talk)

Iana Atanassova

In 8^th International Workshop on Bibliometric-enhanced Information Retrieval (BIR 2019) co-located with 41^st European Conference on Information Retrieval (ECIR 2019), Cologne, Germany, Apr 2019

Bib

@inproceedings{Atanassova2019,
  author = {Atanassova, Iana},
  booktitle = {8<sup>th</sup> International Workshop on Bibliometric-enhanced Information Retrieval (BIR 2019) co-located with 41<sup>st</sup> European Conference on Information Retrieval (ECIR 2019)},
  title = {Beyond Metadata: the New Challenges in Mining Scientific Papers (Keynote talk)},
  month = apr,
  year = {2019},
  location = {Cologne, Germany},
  author+an = {1=me},
}

Determining Citation Blocks using End-to-end Neural Coreference Resolution Model

Marc Bertin, Pierre Jonin, Frederic Armetta, and Iana Atanassova

In 17^th International Conference of the International Society for Scientometrics and Informetrics (ISSI 2019), Sep 2019

Abs Bib

The study of citation contexts is an important element in understanding the function of citations and categorizing the relationships between works. One of the problems in this field is defining the size of citation contexts. In this paper we propose the definition of citation blocks (CB) that are citation contexts composed of one or more sentences that are linked by coreference clusters. We describe the methodology for the automatic processing and determining the boundaries of CB and observe the different sizes of CB in the different sections of the IMRaD structure of articles. The results are obtained from a sample of 70,000 citation contexts extracted from the PLOS dataset.
@inproceedings{Bertin2019, author = {Bertin, Marc and Jonin, Pierre and Armetta, Frederic and Atanassova, Iana}, booktitle = {17th International Conference of the International Society for Scientometrics and Informetrics (ISSI 2019)}, title = {Determining Citation Blocks using End-to-end Neural Coreference Resolution Model}, address = {Rome, Italie}, author+an = {4=me}, month = sep, year = {2019}, }
Identifying the Conceptual Space of Citation Contexts using Coreferences

Marc Bertin, Pierre Jonin, Frédéric Armetta, and Iana Atanassova

In 4^th Joint Workshop on Bibliometric-enhanced Information Retrieval and Natural Language Processing for Digital Libraries (BIRNDL 2019) at the 42^nd International ACM SIGIR Conference), Jul 2019

Abs Bib

The study of citation contexts is an important element in understanding the function of citations and categorizing the relationships between works. One of the problems in this field is defining the size of citation contexts. In this paper we propose the definition of citation blocks (CB) that are citation contexts composed of one or more sentences that are linked by coreference clusters. We describe the methodology for the automatic processing and determining the boundaries of CB and observe the different sizes of CB in the different sections of the IMRaD structure of articles. The results are obtained from a sample of 70,000 citation contexts extracted from the PLOS dataset.
@inproceedings{Bertin2019a, author = {Bertin, Marc and Jonin, Pierre and Armetta, Fr{\'e}d{\'e}ric and Atanassova, Iana}, booktitle = {{4th Joint Workshop on Bibliometric-enhanced Information Retrieval and Natural Language Processing for Digital Libraries (BIRNDL 2019) at the 42nd International ACM SIGIR Conference)}}, title = {{Identifying the Conceptual Space of Citation Contexts using Coreferences}}, editor = {Chandrasekaran, Muthu Kumar and Mayr, Philipp}, pages = {138--144}, volume = {Vol-2414}, address = {Paris, France}, author+an = {4=me}, keywords = {Deep learning ; Citation contexts ; Coreference Resolution}, month = jul, year = {2019} }
Semantically-driven Competitive Intelligence Information Extraction: linguistic model and application

Iana Atanassova, Gan Jin, Ibrahim Soumana, Peter Greenfield, and Sylviane Cardey-Greenfield

In The Eleventh International Conference on Creative Content Technologies (CONTENT 2019), Jul 2019

Abs Bib

In a competitive environment and in the current context of rapid technological advances, competitive intelligence is a key strategic need in the private sector and requires the development of Web content tools capable of robust and semantically-driven text classification. In this paper, we present a method for the information extraction and semantic classification of text segments. Our approach to text processing makes use of linguistic clues to populate an ontology of competitive intelligence. We have developed a method for the automatic identification and classification of sentences into predefined semantic classes by using linguistic models and a knowledge-based approach. This method has been tested on a dataset of journal articles in horology and aeronautics, and can be extended to other domains. The tool that we have developed is part of the WebSO+ platform for competitive intelligence. We present the overall methodology for annotation and information extraction, our experimental protocol and the results obtained from the evaluation.
@inproceedings{Atanassova2019a, author = {Atanassova, Iana and Jin, Gan and Soumana, Ibrahim and Greenfield, Peter and Cardey-Greenfield, Sylviane}, booktitle = {The Eleventh International Conference on Creative Content Technologies (CONTENT 2019)}, title = {{Semantically-driven Competitive Intelligence Information Extraction: linguistic model and application}}, address = {Venice, Italy}, year = {2019}, author+an = {1=me}, }

Special Issues

Mining Scientific Papers: NLP-enhanced Bibliometrics

In Frontiers in Research Metrics and Analytics, Jul 2019

Bib

@incollection{Atanassova2019c,
  booktitle = {Frontiers in Research Metrics and Analytics},
  title = {Mining Scientific Papers: NLP-enhanced Bibliometrics},
  editor = {Atanassova, Iana and Bertin, Marc and Mayr, Philipp},
  editor+an = {1=me},
  issn = {2504-0537},
  year = {2019}
}

2018

Conference Papers

De l’intuition scientifique au moment de l’illumination : étude de "Théorème vivant” par Cédric Villani

Iana Atanassova

In Eurêka ! Le récit savant de découverte et/ou d’invention, Nov 2018

Bib

@inproceedings{Atanassova2018,
  author = {Atanassova, Iana},
  booktitle = {{Eur{\^e}ka ! Le r{\'e}cit savant de d{\'e}couverte et/ou d'invention}},
  title = {{De l'intuition scientifique au moment de l'illumination : {\'e}tude de "Th{\'e}or{\`e}me vivant'' par C{\'e}dric Villani}},
  organization = {{Universit{\'e} de Franche-Comt{\'e} and Centre de Recherches Interdisciplinaires et Transculturelles C.R.I.T. (EA 3224)}},
  address = {Besan{\c c}on, France},
  author+an = {1=me},
  month = nov,
  year = {2018}
}

InTeReC: In-text Reference Corpus for Applying Natural Language Processing to Bibliometrics

Marc Bertin and Iana Atanassova

In 7^th International Workshop on Bibliometric-enhanced Information Retrieval (BIR 2018) in conjunction with the 40^th European Conference on Information Retrieval (ECIR 2018), Mar 2018

Abs Bib

Bibliometrics is more and more interested in the full text processing and the study of the structure of scientific papers. The contexts of in-text references present in articles are particularly relevant for such studies. This work describes the construction of the InTeReC dataset, which is an in-text reference corpus that aims to promote experimental reproducibility and to provide a standard dataset for further research. The InTeReC dataset is a set of sentences containing in-text references together with all the data necessary for their recontextualization in papers using standard CSV format. This should encourage the implementation of natural language processing tools for Bibliometric studies and related research in information retrieval and visualization.
@inproceedings{Bertin2018a, author = {Bertin, Marc and Atanassova, Iana}, booktitle = {{7th International Workshop on Bibliometric-enhanced Information Retrieval (BIR 2018) in conjunction with the 40th European Conference on Information Retrieval (ECIR 2018)}}, title = {{InTeReC: In-text Reference Corpus for Applying Natural Language Processing to Bibliometrics}}, address = {Grenoble, France}, author+an = {2=me}, month = mar, year = {2018} }

Recommending Scientific Papers: The Role of Citation Contexts

Marc Bertin and Iana Atanassova

In 1^st International Conference on Digital Tools & Uses Congress, Oct 2018

Abs DOI Bib

This paper addresses the problem of building recommender systems for scientific papers based on the linguistic and contextual analysis of citation contexts. We explain the importance of taking into consideration citation contexts and the different methodologies that exist as well as the ways that citations impact recommender systems. We also discuss the limits of using citation contexts to generate recommendations.

@inproceedings{Bertin2018b,
  author = {Bertin, Marc and Atanassova, Iana},
  booktitle = {{1<sup>st</sup> International Conference on Digital Tools \& Uses Congress}},
  title = {{Recommending Scientific Papers: The Role of Citation Contexts}},
  doi = {10.1145/3240117.3240123},
  pages = {1--4},
  publisher = {{ACM}},
  address = {Paris, France},
  author+an = {2=me},
  keywords = {Information Retrieval ; Natural Language Processing ; Recommender Systems ; Scientific Papers ; Citation Context Analysis ; Bibliometrics},
  month = oct,
  year = {2018}
}

Studying Uncertainty in Science: a distributional analysis through the IMRaD structure

Iana Atanassova, François-C. Rey, and Marc Bertin

In 7^th International Workshop on Mining Scientific Publications (WOSP 2018) at 11^th edition of the Language Resources and Evaluation Conference (LREC 2018), May 2018

Abs Bib

Uncertainty in science is an integral part of the research process and an important element of discovery. We propose to study the expression of uncertainty in research papers in two domains which are Biomedicine and Physics. We focus on two existing sets of cue words and construct a new set of strong indicators of uncertainty that are composed of linguistic expressions. After processing two datasets that consist of the full text of papers published by PubMed in Open Access, we examine the occurrences of the sets of cue words and strong indicators. As a result, we obtain the distributions of cues of uncertainty along the text progression and their positions with respect to section types in the rethorical structure of the papers. The results show that cues and strong indicators of uncertainty are most frequent in the Discussion section of articles and, in general, towards the end of the text progression. Significant differences can be observed between the two datasets.
@inproceedings{Atanassova2018a, author = {Atanassova, Iana and Rey, Fran{\c c}ois-C. and Bertin, Marc}, booktitle = {{7th International Workshop on Mining Scientific Publications (WOSP 2018) at 11th edition of the Language Resources and Evaluation Conference (LREC 2018)}}, title = {{Studying Uncertainty in Science: a distributional analysis through the IMRaD structure}}, address = {Miyazaki, Japan}, author+an = {1=me;2=student}, month = may, year = {2018} }
Une étude de l’incertitude dans les textes scientifiques : vers la construction d’une ontologie

François-C. Rey, Marc Bertin, and Iana Atanassova

In Terminology & Ontology: Theories and applications (TOTh 2018), Jun 2018

Abs Bib

L’incertitude en sciences est une problématique de nature disciplinaire, liée à l’objet de l’étude et aux méthodologies mises en oeuvre. Cependant, l’enjeu de traiter l’incertitude est essentiel sur le plan sociétal, rappelant la nécessité de disposer d’outils permettant l’analyse du discours scientifique, afin de répondre aux problématiques actuelles. La problématique que nous abordons ici est celle de la compréhension interdisciplinaire et conceptuelle de la notion d’incertitude à travers la constitution et l’étude d’un corpus d’articles scientifiques traitant du changement climatique.
@inproceedings{Rey2018, author = {Rey, Fran{\c c}ois-C. and Bertin, Marc and Atanassova, Iana}, booktitle = {{Terminology \& Ontology: Theories and applications (TOTh 2018)}}, title = {{Une {\'e}tude de l'incertitude dans les textes scientifiques : vers la construction d'une ontologie}}, address = {Chamb{\'e}ry, France}, author+an = {3=me;1=student}, month = jun, year = {2018} }

Datasets

InTeReC: In-text Reference Corpus - Single References Dataset (Version 1.0.0) [Data set]

Marc Bertin and Iana Atanassova

Jun 2018

DOI Bib

@dataset{Bertin2018,
  author = {Bertin, Marc and Atanassova, Iana},
  title = {{InTeReC: In-text Reference Corpus - Single References Dataset (Version 1.0.0) [Data set]}},
  doi = {10.5281/zenodo.1203737},
  booktitle = {{Zenodo}},
  year = {2018},
  author+an = {2=me},
}

2017

proceedings

INFuture2017 - Integrating ICT in Society

Iana Atanassova, Wajdi Zaghouani, Bruno Kragić, Kuldar Aas, Hrvoje Stančić, and 1 more author

Nov 2017

ISSN: 1847-8220

Bib

@proceedings{Atanassova2017a,
  title = {{INFuture2017 - Integrating ICT in Society}},
  editor = {Atanassova, Iana and Zaghouani, Wajdi and Kragi{\'c}, Bruno and Aas, Kuldar and Stan{\v c}i{\'c}, Hrvoje and Seljan, Sanja},
  note = {ISSN: 1847-8220},
  organization = {{Department of Information and Communication Sciences, Faculty of Humanities and Social Sciences, University of Zagreb and The Miroslav Krle{\v z}a Institute of Lexicography}},
  address = {Zagreb, Croatia},
  author = {Atanassova, Iana and Zaghouani, Wajdi and Kragi{\'c}, Bruno and Aas, Kuldar and Stan{\v c}i{\'c}, Hrvoje and Seljan, Sanja},
  booktitle = {{6<sup>th</sup>International Conference The Future of Information Sciences (INFuture)}},
  editor+an = {1=me},
  month = nov,
  year = {2017}
}

Second Workshop on Mining Scientific Papers: Computational Linguistics and Bibliometrics (CLBib 2017)

Iana Atanassova, Marc Bertin, and Philipp Mayr

Oct 2017

ISSN: 1613-0073

Bib

@proceedings{Atanassova2017e,
  title = {{Second Workshop on Mining Scientific Papers: Computational Linguistics and Bibliometrics (CLBib 2017)}},
  editor = {Atanassova, Iana and Bertin, Marc and Mayr, Philipp},
  note = {ISSN: 1613-0073},
  pages = {1--48},
  volume = {2004},
  address = {Wuhan, China},
  author = {Atanassova, Iana and Bertin, Marc and Mayr, Philipp},
  booktitle = {{Second Workshop on Mining Scientific Papers: Computational Linguistics and Bibliometrics co-located with 16<sup>th</sup> International Conference of the International Society for Scientometrics and Informetrics (ISSI 2017)}},
  editor+an = {1=me},
  month = oct,
  year = {2017},
}

Journal Articles

The context of multiple in-text references and their signification

Marc Bertin and Iana Atanassova

International Journal on Digital Libraries, Jul 2017

Abs DOI Bib

In this paper, we consider sentences that contain multiple in-text references (MIR) and their position in the rhetorical structure of articles. We carry out the analysis of MIR in a large-scale dataset of about 80,000 research articles published by the Public Library of Science in 7 journals. We analyze two major characteristics of MIR: their positions in the IMRaD structure of articles and the number of in-text references that make up a MIR in the different journals. We show that MIR are rather frequent in all sections of the rhetorical structure. In the Introduction section, sentences containing MIR account for more than half of the sentences with references. We examine the syntactic patterns that are most used in the contexts of both multiple and single in-text references and show that they are composed, for the most part, of noun groups. We point out the specificity of the Methods section in this respect.
@article{Bertin2017a, author = {Bertin, Marc and Atanassova, Iana}, title = {The context of multiple in-text references and their signification}, doi = {10.1007/s00799-017-0225-7}, issn = {1432-1300}, author+an = {2=me}, day = {21}, journal = {International Journal on Digital Libraries}, month = jul, year = {2017} }

Conference Papers

Création d’une langue contrôlée pour les messages en français et en anglais à destination des piétons pour la mobilité urbaine

Iana Atanassova, Inés Hatira, Camélia El Cadi, and Sylviane Cardey-Greenfield

In FUTURMOB-17: Préparer la transition vers la mobilité autonome, Sep 2017

Bib

@inproceedings{Atanassova2017,
  author = {Atanassova, Iana and Hatira, In{\'e}s and El Cadi, Cam{\'e}lia and Cardey-Greenfield, Sylviane},
  booktitle = {{FUTURMOB-17: Pr{\'e}parer la transition vers la mobilit{\'e} autonome}},
  title = {{Cr{\'e}ation d'une langue contr{\^o}l{\'e}e pour les messages en fran{\c c}ais et en anglais {\`a} destination des pi{\'e}tons pour la mobilit{\'e} urbaine}},
  organization = {{Universit{\'e} Bourgogne Franche-Comt{\'e} and Universit{\'e} de Technologie de Belfort Montb{\'e}liard}},
  address = {Montb{\'e}liard, France},
  author+an = {1=me;2=student;3=student},
  month = sep,
  year = {2017}
}

Editorial for the Second Workshop on Mining Scientific Papers: Computational Linguistics and Bibliometrics (CLBib 2017)

Iana Atanassova, Marc Bertin, and Philipp Mayr

In Second Workshop on Mining Scientific Papers: Computational Linguistics and Bibliometrics co-located with 16^th International Conference of the International Society for Scientometrics and Informetrics (ISSI 2017), Oct 2017

Bib

@inproceedings{Atanassova2017d,
  author = {Atanassova, Iana and Bertin, Marc and Mayr, Philipp},
  booktitle = {{Second Workshop on Mining Scientific Papers: Computational Linguistics and Bibliometrics co-located with 16<sup>th</sup> International Conference of the International Society for Scientometrics and Informetrics (ISSI 2017)}},
  title = {{Editorial for the Second Workshop on Mining Scientific Papers: Computational Linguistics and Bibliometrics (CLBib 2017)}},
  address = {Wuhan, China},
  author+an = {1=me},
  month = oct,
  year = {2017},
}

Information retrieval and semantic annotation of scientific corpora (Keynote speech)

Iana Atanassova

In 6^th International Conference The Future of Information Sciences (INFuture) - Integrating ICT in Society, Nov 2017

Bib

@inproceedings{Atanassova2017b,
  author = {Atanassova, Iana},
  booktitle = {{6<sup>th</sup> International Conference The Future of Information Sciences (INFuture) - Integrating ICT in Society}},
  title = {{Information retrieval and semantic annotation of scientific corpora (Keynote speech)}},
  organization = {{Department of Information and Communication Sciences Faculty of Humanities and Social Sciences, University of Zagreb and The Miroslav Krle{\v z}a Institute of Lexicography}},
  address = {Zagreb, Croatia},
  author+an = {1=me},
  month = nov,
  year = {2017}
}

K-means and Hierarchical Clustering Method to Improve our Understanding of Citation Contexts

Marc Bertin and Iana Atanassova

In Proceedings of the 2^nd Joint Workshop on Bibliometric-enhanced Information Retrieval and Natural Language Processing for Digital Libraries (BIRNDL 2017) co-located with the 40^th International ACM SIGIR Conference, Aug 2017

Abs Bib

In this paper we focus of the clustering of citation contexts in scientific papers. We use two methods, k-means and hierarchical clustering to better understand the phenomenon and types of citations and to explore the multidimensional nature of the elements composing the contexts of citations in different sections of the papers. We have analyzed a data set of seven peer-reviewed academic journals published by PLOS. The obtained clusters show that the Methods section is specific in nature, regardless of the journal. A proximity between some of the journals can be observed.
@inproceedings{Bertin2017, author = {Bertin, Marc and Atanassova, Iana}, booktitle = {{Proceedings of the 2nd Joint Workshop on Bibliometric-enhanced Information Retrieval and Natural Language Processing for Digital Libraries (BIRNDL 2017) co-located with the 40th International ACM SIGIR Conference}}, title = {{K-means and Hierarchical Clustering Method to Improve our Understanding of Citation Contexts}}, pages = {107--112}, volume = {1888}, address = {Tokyo, Japan}, author+an = {2=me}, keywords = {In-text References ; Bibliometrics ; Citation Analysis ; IM- RaD Structure ; Text Mining ; K-means ; hierarchical clustering}, month = aug, year = {2017} }

Langue contrôlée pour un système de messages et alertes dans un environnement de mobilité : gestion de l’ambiguïté phonologique

Nicolas Gutehrlé, Iana Atanassova, and Sylviane Cardey-Greenfield

In FUTURMOB-17: Préparer la transition vers la mobilité autonome, Sep 2017

Bib

@inproceedings{Gutehrle2017,
  author = {Gutehrl{\'e}, Nicolas and Atanassova, Iana and Cardey-Greenfield, Sylviane},
  booktitle = {{FUTURMOB-17: Pr{\'e}parer la transition vers la mobilit{\'e} autonome}},
  title = {{Langue contr{\^o}l{\'e}e pour un syst{\`e}me de messages et alertes dans un environnement de mobilit{\'e} : gestion de l'ambigu{\"i}t{\'e} phonologique}},
  organization = {{Universit{\'e} Bourgogne Franche-Comt{\'e} and Universit{\'e} de Technologie de Belfort Montb{\'e}liard}},
  address = {Montb{\'e}liard, France},
  author+an = {2=me;1=student},
  month = sep,
  year = {2017}
}

Modèle pour un système multilingue d’analyse des opinons et de sentiment

Gan Jin, Iana Atanassova, Ibrahim Soumana, and Sylviane Cardey-Greenfield

In Terminology & Ontology : Théories and applications (TOTh 2017), Jun 2017

Abs Bib

La recherche présentée dans cet article s’inscrit dans le cadre du projet WebSO+ dont l’un des objectifs est de créer un module multilingue d’analyse des opinions et de sentiments dans un système de veille automatique. Ce système vise à contribuer à renforcer l’écosystème des acteurs économiques de l’Arc jurassien franco-suisse, en soutenant les capacités d’innovation, la création de valeur ajoutée et la compétitivité des activités entrepreneuriales, dans un environnement international compétitif, ainsi que dans un contexte général de changements technologiques accélérés et de surcharge informationnelle généralisée. Ainsi, le projet webSO+ a pour objectif de mettre à disposition des entreprises un outil d’intelligence économique performant, qui offre des fonctionnalités de veille (technologique, de marchés, concurrentielle, réglementaire, e-réputation) visant à renforcer la capacité des organisations à agir dans un contexte complexe. En passant par le développement de la veille et de l’intelligence économique, les méthodes et outils permettent aux entreprises qui les maîtrisent de tirer parti des informations stratégiques, afin d’obtenir un avantage concurrentiel, qu’il s’agisse de détecter de nouveaux marchés, de nouveaux produits ou services, d’innover, d’identifier les nouveaux concurrents ainsi que de suivre les faits et gestes des concurrents, et plus généralement, de saisir les opportunités et d’anticiper les risques pour les contourner. Les cantons frontaliers de Suisse occidentale (Jura, Berne, Neuchâtel, Vaud et Genève), ainsi que, les départements frontaliers de la région Bourgogne Franche-Comté (Territoire de Belfort, Doubs et Jura) sont concernés.
@inproceedings{Jin2017, author = {Jin, Gan and Atanassova, Iana and Soumana, Ibrahim and Cardey-Greenfield, Sylviane}, booktitle = {{Terminology \& Ontology : Th\'eories and applications (TOTh 2017)}}, title = {{Mod{\`e}le pour un syst{\`e}me multilingue d'analyse des opinons et de sentiment}}, organization = {{University of Savoie}}, address = {Chamb{\'e}ry, France}, author+an = {2=me}, month = jun, year = {2017} }

What can we learn by processing scientific papers? Looking for the invariants of scientific writing

Iana Atanassova

In Seminaire, Jun 2017

Bib

@inproceedings{Atanassova2017c,
  author = {Atanassova, Iana},
  booktitle = {Seminaire},
  title = {{What can we learn by processing scientific papers? Looking for the invariants of scientific writing}},
  organization = {Research Group in Computational Linguistics (RGCL), Université de Woverhampton},
  address = {Royaume Uni},
  year = {2017},
  author+an = {1=me},
}

2016

Journal Articles

On the composition of scientific abstracts

Iana Atanassova, Marc Bertin, and Vincent Larivière

Journal of Documentation, Jun 2016

Abs DOI Bib

Purpose – Scientific abstracts reproduce only part of the information and the complexity of argumentation in a scientific article. The purpose of this paper provides a first analysis of the similarity between the text of scientific abstracts and the body of articles, using sentences as the basic textual unit. It contributes to the understanding of the structure of abstracts. Design/methodology/approach – Using sentence-based similarity metrics, the authors quantify the phenomenon of text re-use in abstracts and examine the positions of the sentences that are similar to sentences in abstracts in the introduction, methods, results and discussion structure, using a corpus of over 85,000 research articles published in the seven Public Library of Science journals. Findings – The authors provide evidence that 84 percent of abstract have at least one sentence in common with the body of the paper. Studying the distributions of sentences in the body of the articles that are re-used in abstracts, the authors show that there exists a strong relation between the rhetorical structure of articles and the zones that authors re-use when writing abstracts, with sentences mainly coming from the beginning of the introduction and the end of the conclusion. Originality/value – Scientific abstracts contain what is considered by the author(s) as information that best describe documents’ content. This is a first study that examines the relation between the contents of abstracts and the rhetorical structure of scientific articles. The work might provide new insight for improving automatic abstracting tools as well as information retrieval approaches, in which text organization and structure are important features.
@article{Atanassova2016c, author = {Atanassova, Iana and Bertin, Marc and Larivière, Vincent}, title = {On the composition of scientific abstracts}, doi = {10.1108/JDOC-09-2015-0111}, issn = {0022-0418}, number = {4}, pages = {636--647}, volume = {72}, journal = {Journal of Documentation}, year = {2016}, author+an = {1=me}, keywords = {Information retrieval, Algorithms, Information science and documentation, Abstracting, Abstracts, Text retrieval} }
Temporal Properties of Recurring In-text References

Iana Atanassova and Marc Bertin

D-Lib Magazine, Jun 2016

Abs DOI Bib

In this paper we study the properties of recurring in-text references in research articles and more specifically their positions in the rhetorical structure of articles and their age with respect to the citing article. We have processed a large scale corpus of approximately 80,000 papers published by PLOS (Public Library of Science). We examine the number and types of recurring in-text references, as well as their age according to positions in the IMRaD structure. (Introduction, Methods, Results, and Discussion). The results show that the age of recurring references varies considerably in all sections and journals. While they are especially dense in the Introduction section, most of them reappear in the beginning of the Results and the Discussion sections. We also observe that the beginning of the Methods and the Results sections share a significant number of recurring references.
@article{Atanassova2016d, author = {Atanassova, Iana and Bertin, Marc}, title = {Temporal Properties of Recurring In-text References}, doi = {10.1045/september2016-atanassova}, issn = {1082-9873}, number = {22}, volume = {9/10}, journal = {D-Lib Magazine}, year = {2016}, url = {https://www.dlib.org/dlib/september16/atanassova/09atanassova.html}, author+an = {1=me}, }
The Invariant Distribution of References in Scientific Articles

Marc Bertin, Iana Atanassova, Vincent Larivière, and Yves Gingras

Journal of the Association for Information Science and Technology (JASIST), Jun 2016

Abs DOI Bib

The organization of scientific papers typically follows a standardized pattern, the well-known IMRaD structure (Introduction, Methods, Results, and Discussion). Using the full text of 45,000 papers published in the PLoS series of journals as a case study, this paper investigates, from the viewpoint of bibliometrics, how references are distributed along the structure of scientific papers, as well as the age of these cited references. It shows that, once the sections of articles are realigned to follow the IMRaD sequence, the position of cited references along the text of articles is invariant across all PLoS journals, with the introduction and conclusion accounting for most of the references. It also provides evidence that the age of cited references varies quite a lot by section, with older references being found in the methods and more recent ones in the discussion. On the whole, these results provide insight into the different roles citations have in the scholarly communication process.
@article{Bertin2016a, author = {Bertin, Marc and Atanassova, Iana and Larivière, Vincent and Gingras, Yves}, title = {The Invariant Distribution of References in Scientific Articles}, doi = {10.1002/asi.23367}, issn = {2330-1643}, number = {1}, pages = {164--177}, url = {https://hal.science/hal-01742169v1}, volume = {67}, author+an = {2=me}, journal = {Journal of the Association for Information Science and Technology (JASIST)}, year = {2016} }
The Linguistic Patterns and Rhetorical Structure of Citation Context: an approach using n-grams

Marc Bertin, Iana Atanassova, Cassidy R. Sugimoto, and Vincent Lariviere

Scientometrics, Jun 2016

Abs DOI Bib

Using the full-text corpus of more than 75,000 research articles published by seven PLOS journals, this paper proposes a natural language processing approach for identifying the function of citations. Citation contexts are assigned based on the frequency of n-gram co-occurrences located near the citations. Results show that the most frequent linguistic patterns found in the citation contexts of papers vary according to their location in the IMRaD structure of scientific articles. The presence of negative citations is also dependent on this structure. This methodology offers new perspectives to locate these discursive forms according to the rhetorical structure of scientific articles, and will lead to a better understanding of the use of citations in scientific articles.
@article{Bertin2016b, author = {Bertin, Marc and Atanassova, Iana and Sugimoto, Cassidy R. and Lariviere, Vincent}, title = {The Linguistic Patterns and Rhetorical Structure of Citation Context: an approach using n-grams}, doi = {10.1007/s11192-016-2134-8}, issn = {0138-9130}, number = {109}, pages = {1417--1434}, volume = {3}, url = {https://shs.hal.science/halshs-01742166v1}, journal = {Scientometrics}, year = {2016}, author+an = {2=me}, }

Conference Papers

Étude lexicale de textes arabes pour l’évaluation automatique de la complexité textuelle

Youcef Ihab Morsi, Yves Bordet, and Iana Atanassova

In 7^e Colloque International en Traductologie et TAL (TRADETAL 2016), May 2016

Abs Bib

Nous proposons une méthode pour évaluer la complexité du vocabulaire des textes en langue arabe en utilisant les résultats d’une analyse lexicale d’un corpus littéraire composé de 40 textes. Cette approche a été proposée par Yves Bordet dans le projet Doxilog appliqué à plusieurs langues, dont le français, l’anglais, l’espagnol, le russe et le chinois. La présence du vocabulaire arabe pérenne dans un texte en arabe est un élément clé permettant de déterminer la complexité du texte et notamment l’âge et le niveau d’études pour les apprenants natifs et le niveau de maîtrise de la langue pour les apprenants de langues étrangères.
@inproceedings{Morsi2016, author = {Morsi, Youcef Ihab and Bordet, Yves and Atanassova, Iana}, booktitle = {{7e Colloque International en Traductologie et TAL (TRADETAL 2016)}}, title = {{{\'E}tude lexicale de textes arabes pour l'{\'e}valuation automatique de la complexit{\'e} textuelle}}, address = {Oran, Algeria}, author+an = {3=me;1=student}, month = may, year = {2016} }
Génération d’exercices d’apprentissage de langue de spécialité par l’exploration du corpus

François-C. Rey, Izabella Thomas, and Iana Atanassova

In Atelier Enseignement des langues et TAL (ELTAL), Jul 2016

Abs Bib

Il n’existe pas de travaux sur des logiciels dédiés à l’apprentissage des langues de spécialité, ni à la création de ressources pédagogiques spécifiques. Les outils informatisés concernant les langues de spécialité se limitent aux logiciels d’aide à la traduction et à des outils d’aide au recensement terminologique. Afin de doter les enseignants de langues étrangères de spécialité d’outils prenant en compte leurs besoins spécifiques nous proposons de concevoir et de développer une plateforme pour la génération de matériels pédagogiques dans le domaine des langues de spécialités. Pour répondre à cet objectif, nous avons effectué une première expérimentation concernant la génération automatique d’exercices d’apprentissage du vocabulaire spécialisé. Nous avons choisi la génération d’exercices à trous basés sur les phrases tirées d’un corpus de textes authentiques. Les résultats de ces premières expérimentations montrent la faisabilité de la génération d’exercices à trous, à partir de listes de vocabulaire et d’un corpus spécialisés intégrés à la plateforme, ainsi que de textes fournis par un enseignant.
@inproceedings{Rey2016, author = {Rey, Fran{\c c}ois-C. and Thomas, Izabella and Atanassova, Iana}, booktitle = {{Atelier Enseignement des langues et TAL (ELTAL)}}, title = {{G{\'e}n{\'e}ration d'exercices d'apprentissage de langue de sp{\'e}cialit{\'e} par l'exploration du corpus}}, organization = {{Inalco}}, series = {Actes de la conf{\'e}rence conjointe JEP-TALN-RECITAL 2016}, volume = {9}, address = {Paris, France}, author+an = {3=me;1=student}, month = jul, year = {2016} }
Interfacing the Domain of Global Security with Natural Language Processing: the Role of Language Modelling

Iana Atanassova, Marc Bertin, Sylviane Cardey, and Peter Greenfield

In The Tenth International Conference on Natural Language Processing (HrTAL 2016), Sep 2016

Abs Bib

This paper presents different aspects of natural language processing (NLP) applications in the domain of global security dealing with human language. NLP is confronted with the need of linguistic models that can reliably support the conception and deployment of tools related to crisis management in various situations. The need for mission-critical applications incorporating the use or presence of human language is widespread, for example in situations that entail needs in translation, information retrieval, human-computer interaction, etc. We focus more precisely on Human Language Modelling and present the use of NLP approaches for various applications in the context of risk management and security.
@inproceedings{Atanassova2016b, author = {Atanassova, Iana and Bertin, Marc and Cardey, Sylviane and Greenfield, Peter}, booktitle = {{The Tenth International Conference on Natural Language Processing (HrTAL 2016)}}, title = {{Interfacing the Domain of Global Security with Natural Language Processing: the Role of Language Modelling}}, number = {82}, pages = {249--252}, series = {Suvremena lingvistika}, volume = {42}, address = {Dubrovnik, Croatia}, author+an = {1=me}, month = sep, year = {2016} }

Mining Scientific Papers: Structure, Citations, Semantics

Iana Atanassova

In Seminar, Sep 2016

Bib

@inproceedings{Atanassova2016,
  author = {Atanassova, Iana},
  booktitle = {Seminar},
  title = {{Mining Scientific Papers: Structure, Citations, Semantics}},
  organization = {Centre for Science and Technology Studies (CWTS)},
  address = {Leiden, Pays Bas},
  author+an = {1=me},
  year = {2016}
}

Multiple In-text Reference Phenomenon

Marc Bertin and Iana Atanassova

In Workshop on Bibliometric-enhanced Information Retrieval and NLP for Digital Libraries (BIRNDL 2016) co-located with the Joint Conference on Digital Libraries (JCDL 2016), Jun 2016

Abs Bib

In this paper we consider sentences that contain Multiple In-text References (MIR) and their position in the rhetorical structure of articles. We carry out the analysis of MIR in a large scale dataset of about 80,000 research articles published by the Public Library of Science in 7 journals. We analyze two major characteristics of MIR: their positions in the IMRaD structure of articles, and the number of in-text references that make up a MIR in the different journals. We show that MIR are rather frequent in all sections of the rhetorical structure. In the Introduction section, sentences containing MIR account for more than half of the sentences with references.
@inproceedings{Bertin2016, author = {Bertin, Marc and Atanassova, Iana}, booktitle = {{Workshop on Bibliometric-enhanced Information Retrieval and NLP for Digital Libraries (BIRNDL 2016) co-located with the Joint Conference on Digital Libraries (JCDL 2016)}}, title = {{Multiple In-text Reference Phenomenon}}, number = {2-3}, pages = {14--22}, volume = {19}, address = {Newark, NJ, United States}, author+an = {2=me}, keywords = {Multiple In-text References ; Citation Analysis ; Bibliometrics ; Content Citation Analysis ; IMRaD structure ; In-text References}, month = jun, year = {2016} }
Weak Links and Strong Meaning: The Complex Phenomenon of Negational Citations

Marc Bertin and Iana Atanassova

In Bibliometric-enhanced Information Retrieval (BIR 2016) co-located with the 38^th European Conference on Information Retrieval (ECIR 2016), Mar 2016

Abs Bib

The latest advances in research in the field of bibliometrics take into consideration in-text references. The purpose of this paper is to focus on citation contexts that express negational citations and which are relatively rare in articles. Our goal is to automate the extraction of negational citation contexts and to put them in relation to positions in the text progression of articles. After extracting sentences from the full text body of articles, we construct linguistic resources in order to identify some of the negational citation discursive patterns. We show the distribution of negational citations in the IMRaD structure. The identification of negational citations has numerous potential applications and might be used to improve information retrieval of scientific papers.
@inproceedings{Bertin2016c, author = {Bertin, Marc and Atanassova, Iana}, booktitle = {{Bibliometric-enhanced Information Retrieval (BIR 2016) co-located with the 38th European Conference on Information Retrieval (ECIR 2016)}}, title = {{Weak Links and Strong Meaning: The Complex Phenomenon of Negational Citations}}, editor = {Mayr, Philipp and Frommholz, Ingo and Cabanac, Guillaume}, pages = {14--25}, publisher = {{CEUR Workshop Proceedings}}, volume = {Vol-1567}, address = {Padova, Italy}, author+an = {2=me}, keywords = {Citation Context Analysis In-text References ; Bibliometrics ; Semantic Annotation ; IMRaD ; Negative Citations}, month = mar, year = {2016} }

Miscellaneous

TDM Stories: The Structure of Papers

Iana Atanassova

Mar 2016

Bib

@misc{Atanassova2016a,
  author = {Atanassova, Iana},
  booktitle = {OpenMinTed Communications},
  title = {TDM Stories: The Structure of Papers},
  url = {https://www.youtube.com/watch?v=Gn4_ZgBBgwg&list=PLJUx52iHEnRJtt6i9OSE41JYledLaPBJ1},
  author+an = {1=me},
  year = {2016}
}

2015

proceedings

Atelier "Traitement Automatique des Langues Slaves" (TASLA)

, Caen, Mar 2015

Bib

@proceedings{Kostov2015,
  title = {Atelier "Traitement Automatique des Langues Slaves" (TASLA)},
  editor = {Kostov, Jovan and Thomas, Izabella and Atanassova, Iana},
  location = {Caen},
  series = {22<sup>e</sup> Conférence sur le Traitement Automatique des Langues Naturelles (TALN 2015)},
  address = {Caen},
  year = {2015},
  editor+an = {3=me},
}

First Workshop on Mining Scientific Papers: Computational Linguistics and Bibliometrics (CLBib 2015)

Iana Atanassova, Marc Bertin, and Philipp Mayr

Jun 2015

ISSN: 1613-0073

Bib

@proceedings{Atanassova2015d,
  title = {{First Workshop on Mining Scientific Papers: Computational Linguistics and Bibliometrics (CLBib 2015)}},
  editor = {Atanassova, Iana and Bertin, Marc and Mayr, Philipp},
  note = {ISSN: 1613-0073},
  pages = {1--49},
  volume = {1384},
  address = {Istanbul, Turkey},
  author = {Atanassova, Iana and Bertin, Marc and Mayr, Philipp},
  booktitle = {{First Workshop on Mining Scientific Papers: Computational Linguistics and Bibliometrics co-located with 15<sup>th</sup> International Conference of the International Society for Scientometrics and Informetrics (ISSI 2015)}},
  editor+an = {1=me},
  issn = {1613-0073},
  month = jun,
  year = {2015},
}

Journal Articles

Cartographie linguistique des références citées

Marc Bertin, Iana Atanassova, Vincent Larivière, and Yves Gingras

Découvrir, le magazine de l’Association Francophone pour le savoir (ACFAS), Jun 2015

Bib

@article{Bertin2015,
  author = {Bertin, Marc and Atanassova, Iana and Larivière, Vincent and Gingras, Yves},
  title = {Cartographie linguistique des références citées},
  journal = {Découvrir, le magazine de l'Association Francophone pour le savoir (ACFAS)},
  year = {2015},
  url = {https://www.acfas.ca/publications/magazine/2015/03/cartographie-linguistique-references-citees},
  author+an = {2=me},
}

Mapping the Linguistic Context of Citations

Marc Bertin, Iana Atanassova, Vincent Larivière, and Yves Gingras

Bulletin of the Association for Information Science and Technology (ASIST) Featuring the “The Future of Science Mapping”, Jan 2015

Abs DOI Bib

Scientific papers are routinely structured in sections for introduction, methods, research and discussion, a standard since the 1970s. Citations originating within each section serve different purposes and can be meaningfully classified according to position, shedding light on an author’s purpose for the citation. Furthermore, words near the citations in the various sections differ, providing the basis for lexical and semantic analysis of citation contexts. Approximately 50,000 scientific papers from seven PLOS journals published between 2009 and 2012 were analyzed for citation use within the identifiable document structure and for verbs used in the context of the citations. Frequencies of verbs in the four section types demonstrate the predominant use of certain words by section. Introduction sections showed greater variety of verbs, while a more limited range of verbs was seen in Methods sections. The lexical distribution process may be applied to other contexts supporting text processing based on XML format.
@article{Bertin2015c, author = {Bertin, Marc and Atanassova, Iana and Larivière, Vincent and Gingras, Yves}, title = {{Mapping the Linguistic Context of Citations}}, doi = {10.1002/bult.2015.1720410208}, issn = {2373-9223}, number = {2}, url = {https://asistdl.onlinelibrary.wiley.com/doi/10.1002/bult.2015.1720410208}, volume = {41}, author+an = {2=me}, journal = {{Bulletin of the Association for Information Science and Technology (ASIST) Featuring the “The Future of Science Mapping”}}, month = jan, year = {2015} }

Conference Papers

Analyse logométrique des revues québécoises : traitements et visualisations

Iana Atanassova, Jean-Philippe Warren, and Marc Bertin

In Colloque: Relire les revues québécoises : histoires, formes et pratiques, Oct 2015

Bib

@inproceedings{Atanassova2015a,
  author = {Atanassova, Iana and Warren, Jean-Philippe and Bertin, Marc},
  booktitle = {{Colloque: Relire les revues qu{\'e}b{\'e}coises : histoires, formes et pratiques}},
  title = {{Analyse logom{\'e}trique des revues qu{\'e}b{\'e}coises : traitements et visualisations}},
  address = {Montr{\'e}al, Canada},
  author+an = {1=me},
  month = oct,
  year = {2015}
}

Characterizing In-text Citations using N-gram Distributions

Marc Bertin and Iana Atanassova

In 15^th International Conference of the International Society for Scientometrics and Informetrics (ISSI 2015), Jun 2015

Bib

@inproceedings{Bertin2015a,
  author = {Bertin, Marc and Atanassova, Iana},
  booktitle = {{15<sup>th</sup> International Conference of the International Society for Scientometrics and Informetrics (ISSI 2015)}},
  title = {{Characterizing In-text Citations using N-gram Distributions}},
  editor = {et al., Albert Ali Salah},
  address = {Istanbul, Turkey},
  author+an = {2=me},
  month = jun,
  year = {2015},
}

Editorial for the First Workshop on Mining Scientific Papers: Computational Linguistics and Bibliometrics (CLBib 2015)

Iana Atanassova, Marc Bertin, and Philipp Mayr

In First Workshop on Mining Scientific Papers: Computational Linguistics and Bibliometrics co-located with 15^th International Conference of the International Society for Scientometrics and Informetrics (ISSI 2015), Jun 2015

Bib

@inproceedings{Atanassova2015b,
  author = {Atanassova, Iana and Bertin, Marc and Mayr, Philipp},
  booktitle = {{First Workshop on Mining Scientific Papers: Computational Linguistics and Bibliometrics co-located with 15<sup>th</sup> International Conference of the International Society for Scientometrics and Informetrics (ISSI 2015)}},
  title = {{Editorial for the First Workshop on Mining Scientific Papers: Computational Linguistics and Bibliometrics (CLBib 2015)}},
  pages = {1--4},
  volume = {1384},
  address = {Istanbul, Turkey},
  author+an = {1=me},
  month = jun,
  year = {2015},
}

Exploitation de données spatiales provenant d’articles scientifiques pour le suivi des maladies tropicales

Iana Atanassova, Marc Bertin, and Tomi Kauppinen

In Gestion et Analyse des données Spatiales et Temporelles (GAST’2015), 15^e conférence internationale sur l’extraction et la gestion des connaissances (EGC 2015), Jan 2015

Abs Bib

Nous nous intéressons à la représentation des informations géographiques extraites d’articles scientifiques. En utilisant des outils de Traitement Automatique des Langues et de géo-codage, nous avons traité la revue PLOS Neglected Tropical Diseases afin de produire des données spatiales liées aux articles sous forme de Linked Data. Les résultats montrent une exploitation spatiale et temporelle des données représentant les zones du monde concernées par les maladies tropicales à différentes échelles.

@inproceedings{Atanassova2015c,
  author = {Atanassova, Iana and Bertin, Marc and Kauppinen, Tomi},
  booktitle = {{Gestion et Analyse des donn{\'e}es Spatiales et Temporelles (GAST'2015), 15<sup>e</sup> conf{\'e}rence internationale sur l'extraction et la gestion des connaissances (EGC 2015)}},
  title = {{Exploitation de donn{\'e}es spatiales provenant d'articles scientifiques pour le suivi des maladies tropicales}},
  editor = {Guyet, Thomas and {\'E}ric Kergosien},
  pages = {21--32},
  address = {Luxembourg},
  author+an = {1=me},
  keywords = {Linked Data ; g{\'e}ocodage ; Natural Language Processing ; Spatio-temporal Management and Analysis ; Gestion et Analyse Spatio-temporelles ; Traitement Automatique du Langage Naturel ; PLOS ; geocoding ; Web des donn{\'e}es},
  month = jan,
  year = {2015}
}

Factorial correspondence analysis applied to citation contexts

Marc Bertin and Iana Atanassova

In Conference: 2^nd International Workshop on Bibliometric-enhanced Information Retrieval (BIR 2015) at the 37^th European Conference on Information Retrieval (ECIR 2015), Mar 2015

Bib

@inproceedings{Bertin2015b,
  author = {Bertin, Marc and Atanassova, Iana},
  booktitle = {{Conference: 2<sup>nd</sup> International Workshop on Bibliometric-enhanced Information Retrieval (BIR 2015) at the 37<sup>th</sup> European Conference on Information Retrieval (ECIR 2015)}},
  title = {{Factorial correspondence analysis applied to citation contexts}},
  pages = {22--29},
  volume = {1344},
  address = {Vienne, Austria},
  author+an = {2=me},
  month = mar,
  year = {2015}
}

Fouille textuelle de revues intellectuelles québécoises

Iana Atanassova

In 83^e congrès de l’ACFAS (Association francophone pour le savoir), "Une plateforme pour la recherche et l’expérimentation", Mar 2015

Bib

@inproceedings{Atanassova2015,
  author = {Atanassova, Iana},
  booktitle = {83<sup>e</sup> congr\`es de l'ACFAS (Association francophone pour le savoir), "Une plateforme pour la recherche et l'exp\'erimentation"},
  title = {Fouille textuelle de revues intellectuelles qu\'eb\'ecoises},
  author+an = {1=me},
  year = {2015}
}

Mining Scientific Papers for Bibliometrics: a (very) Brief Survey of Methods and Tools

Iana Atanassova, Marc Bertin, and Philipp Mayr

In 15^th International Society of Scientometrics and Informetrics Conference (ISSI 2015), Jun 2015

Abs Bib

The Open Access movement in scientific publishing and search engines like Google Scholar have made scientific articles more broadly accessible. During the last decade, the availability of scientific papers in full text has become more and more widespread thanks to the growing number of publications on online platforms such as ArXiv and CiteSeer (Wu, 2014). The efforts to provide articles in machine-readable formats and the rise of Open Access publishing have resulted in a number of standardized formats for scientific papers (such as NLM-JATS, TEI, DocBook).
@inproceedings{Atanassova2015e, author = {Atanassova, Iana and Bertin, Marc and Mayr, Philipp}, booktitle = {{15th International Society of Scientometrics and Informetrics Conference (ISSI 2015)}}, title = {{Mining Scientific Papers for Bibliometrics: a (very) Brief Survey of Methods and Tools}}, address = {Istanbul, Turkey}, author+an = {1=me}, month = jun, year = {2015}, }
The Linguistic Context of Citations: a Cartography of the Structure of Scientific Papers

Marc Bertin, Iana Atanassova, Vincent Larivière, and Yves Gingras

In American Association for the Advancement of Science (AAAS) Annual Meeting - Innovations, Information, and Imaging, Feb 2015

Abs Bib

The IMRaD structure of scientific papers (Introduction, Methods, Results, and Discussion) has been adopted by most journals and has become standard in the 1970s. It was introduced to facilitate the reading of publications and to provide faster access to information by standardizing the argumentative structure of articles. The IMRaD sequence provides an outline for scientific writing, dividing the articles into four sections, each one having a specific rhetorical function. Previous studies on the density of citations in the four main section types have showed that the distribution of references along the text progression is essentially invariant for the seven PLOS journals. In this study, we use Natural Language Processing tools to look into the way authors use citations in the different sections, in order to build visualizations of the inner structure of scientific articles. We have processed the dataset of articles published in the seven PLOS journals over the period 2009-2012. This dataset contains about 50,000 scientific papers, mainly in the fields of Biology and Medicine. We consider that verbs found in sentences containing citations are an important indicator of the purpose of citations and of the reasons behind citing a given document. Thus the linguistic context of citations indicates the relations that exist between authors. By processing the section titles, we have identified the different sections of the papers as well as the positions of citations in these sections. Citations were then linked with the verb occurrences in citation contexts using the Stanford POS-tagger. The data on the verb frequencies in the four section types and their positions in the text were visualized using Circos tool to produce a circular layout showing the verbs along the text progression. Our results demonstrate a strong relation between verbs used around citations and the rhetorical structure of scientific papers. Furthermore, we provide context tree visualizations for the set of verbs and multi-layer author network maps, generated using Gephi, where relations between authors are considered in terms of the position of citations in the IMRaD structure. By processing the full text of scientific publications, we achieve a detailed representation of the phenomenon of citations. This approach provides a novel framework for the study of relations between authors in the field of Big Humanities. Our ultimate goal is to design interactive domain-specific maps that could be exploited as tool for improved information extraction and analysis of citation networks.
@inproceedings{Bertin2015d, author = {Bertin, Marc and Atanassova, Iana and Larivi{\`e}re, Vincent and Gingras, Yves}, booktitle = {{American Association for the Advancement of Science (AAAS) Annual Meeting - Innovations, Information, and Imaging}}, title = {{The Linguistic Context of Citations: a Cartography of the Structure of Scientific Papers}}, address = {San Jose, California, United States}, author+an = {2=me}, month = feb, year = {2015} }

Towards the Enrichment of Terminological Resources by Scientific Corpora Analysis

Izabella Thomas and Iana Atanassova

In Electronic lexicography in the 21^th century Conference: Linking lexical data in the digital age (eLex 2015), Feb 2015

Bib

@inproceedings{Thomas2015,
  author = {Thomas, Izabella and Atanassova, Iana},
  title = {Towards the Enrichment of Terminological Resources by Scientific Corpora Analysis},
  booktitle = {Electronic lexicography in the 21<sup>th</sup> century Conference: Linking lexical data in the digital age (eLex 2015)},
  year = {2015},
  address = {United Kingdom},
  author+an = {2=me},
}

2014

Conference Papers

A study of lexical distribution in citation contexts through the IMRaD standard

Marc Bertin and Iana Atanassova

In Proceedings of the 1^st Workshop on Bibliometric-enhanced Information Retrieval (BIR 2014) co-located with 36^th European Conference on Information Retrieval (ECIR 2014), Apr 2014

Bib

@inproceedings{Bertin2014,
  author = {Bertin, Marc and Atanassova, Iana},
  booktitle = {{Proceedings of the 1<sup>st</sup> Workshop on Bibliometric-enhanced Information Retrieval (BIR 2014) co-located with 36<sup>th</sup> European Conference on Information Retrieval (ECIR 2014)}},
  title = {{A study of lexical distribution in citation contexts through the IMRaD standard}},
  pages = {5--12},
  volume = {1143},
  address = {Amsterdam, Netherlands},
  author+an = {2=me},
  keywords = {Content Citation Analysis ; Citation Contexts ; Bibliographic References ; IMRaD ; Citation Acts ; Lexical Distribution},
  month = apr,
  year = {2014}
}

Faceted Semantic Search for Scientic Papers

Iana Atanassova and Marc Bertin

In Semantic Publishing Challenge co-located with 11^th European Semantic Web Conference (ESWC 2014), May 2014

Bib

@inproceedings{Atanassova2014,
  author = {Atanassova, Iana and Bertin, Marc},
  booktitle = {{Semantic Publishing Challenge co-located with 11<sup>th</sup> European Semantic Web Conference (ESWC 2014)}},
  title = {{Faceted Semantic Search for Scientic Papers}},
  address = {Anissaras, Greece},
  author+an = {1=me},
  keywords = {Semantic Annotation ; Information Retrieval ; Faceted Search ; Semantic Facets ; Solr},
  month = may,
  year = {2014}
}

Fouille textuelle, extraction et catégorisation de contextes de citations pour les articles scientifiques

Marc Bertin and Iana Atanassova

In 82^e Congrès de l’ACFAS (Association francophone pour le savoir), LNISC 2014 Langues Naturelles, Informatique et Sciences Cognitives Colloque 635, May 2014

Bib

@inproceedings{Bertin2014a,
  author = {Bertin, Marc and Atanassova, Iana},
  booktitle = {82<sup>e</sup> Congr{\`e}s de l'ACFAS (Association francophone pour le savoir), LNISC 2014 Langues Naturelles, Informatique et Sciences Cognitives Colloque 635},
  title = {{Fouille textuelle, extraction et cat{\'e}gorisation de contextes de citations pour les articles scientifiques}},
  address = {Montr{\'e}al, Canada},
  author+an = {2=me},
  month = may,
  year = {2014}
}

Hybrid Approach for the Semantic Processing of Scientic Papers

Marc Bertin and Iana Atanassova

In Semantic Publishing Challenge co-located with 11^th European Semantic Web Conference (ESWC 2014), May 2014

Bib

@inproceedings{Bertin2014b,
  author = {Bertin, Marc and Atanassova, Iana},
  booktitle = {{Semantic Publishing Challenge co-located with 11<sup>th</sup> European Semantic Web Conference (ESWC 2014)}},
  title = {{Hybrid Approach for the Semantic Processing of Scientic Papers}},
  address = {Anissaras, Crete, Greece},
  author+an = {2=me},
  keywords = {Semantic Annotation ; Citation Acts ; CRF ; RDF graphs},
  month = may,
  year = {2014}
}

Book Chapters

Semantic Web Evaluation Challenge: SemWebEval 2014 at ESWC 2014

Iana Atanassova and Marc Bertin

May 2014

Abs Bib

We present an Information Retrieval System for scientific publications that provides the possibility to filter results according to semantic facets. We use sentence-level semantic annotations that identify specific semantic relations in texts, such as methods, definitions, hypotheses, that correspond to common information needs related to scientific literature. The semantic annotations are obtained using a rule-based method that identifies linguistic clues organized into a linguistic ontology. The system is implemented using Solr Search Server and offers efficient search and navigation in scientific papers.
@inbook{Atanassova2014a, author = {Atanassova, Iana and Bertin, Marc}, booktitle = {Communications in Computer and Information Science}, title = {Semantic Web Evaluation Challenge: SemWebEval 2014 at ESWC 2014}, chapter = {Semantic Facets for Scientific Information Retrieval}, editor = {et al., Valentina Presutti}, isbn = {978-3-319-12024-9}, pages = {108--113}, publisher = {Springer}, author+an = {1=me}, month = may, year = {2014} }

Semantic Web Evaluation Challenge: SemWebEval 2014 at ESWC 2014

Marc Bertin and Iana Atanassova

May 2014

Bib

@inbook{Bertin2014c,
  author = {Bertin, Marc and Atanassova, Iana},
  booktitle = {Communications in Computer and Information Science},
  title = {Semantic Web Evaluation Challenge: SemWebEval 2014 at ESWC 2014},
  chapter = {Extraction and Characterization of Citations in Scientific Papers},
  editor = {et al., Valentina Presutti},
  isbn = {978-3-319-12024-9},
  pages = {120--128},
  publisher = {Springer},
  author+an = {2=me},
  month = may,
  year = {2014}
}

Miscellaneous

The Linguistic Context of Citations

Marc Bertin, Iana Atanassova, Vincent Larivière, and Yves Gingras

May 2014

Bib

@misc{Bertin2014d,
  author = {Bertin, Marc and Atanassova, Iana and Larivi{\`e}re, Vincent and Gingras, Yves},
  booktitle = {{10<sup>th</sup> Iteration (2014): The Future of Science Mapping,'' Places \& Spaces: Mapping Science}},
  title = {{The Linguistic Context of Citations}},
  organization = {{Katy B{\"o}rner and Samuel Mills}},
  url = {https://scimaps.org/map/10/6},
  address = {Indiana, United States},
  year = {2014},
  author+an = {2=me},
}

2013

Conference Papers

The distribution of references in scientific papers: An analysis of the IMRaD structure

Marc Bertin, Iana Atanassova, Vincent Larivière, and Yves Gingras

In 14^th International Conference of the International Society for Scientometrics and Informetrics (ISSI 2013), Jul 2013

Bib

@inproceedings{Bertin2013,
  author = {Bertin, Marc and Atanassova, Iana and Larivi{\`e}re, Vincent and Gingras, Yves},
  booktitle = {{14<sup>th</sup> International Conference of the International Society for Scientometrics and Informetrics (ISSI 2013)}},
  title = {{The distribution of references in scientific papers: An analysis of the IMRaD structure}},
  pages = {591--603},
  volume = {1},
  address = {Vienne, Austria},
  author+an = {2=me},
  month = jul,
  year = {2013},
}

2012

Theses

Exploitation informatique des annotations sémantiques automatiques d’Excom pour la recherche d’informations et la navigation

Iana Atanassova

Université Paris-Sorbonne (Paris-IV), sous la direction de Pr. Jean-Pierre Desclés, Jan 2012

Bib

@phdthesis{Atanassova2012,
  author = {Atanassova, Iana},
  title = {Exploitation informatique des annotations sémantiques automatiques d'Excom pour la recherche d'informations et la navigation},
  address = {Paris, France},
  author+an = {1=me},
  keywords = {Information retrieval, Semantic annotation, Contextual exploration, Information extraction, Ranking algorithm},
  month = jan,
  school = {Universit\'{e} Paris-Sorbonne (Paris-IV), sous la direction de Pr. Jean-Pierre Desclés},
  title-en = {Information Retrieval and Text Navigation through the Exploitation of the Automatic Semantic Annotation of the Excom Engine},
  year = {2012}
}

Journal Articles

Semantic Enrichment of Scientific Publications and Metadata: Citation Analysis Through Contextual and Cognitive Analysis

Marc Bertin and Iana Atanassova

D-Lib Magazine, Jul 2012

Abs DOI Bib

The last several years have seen the emergence of digital libraries from which documents are harvested using the OAI-PMH protocol. Considering the volume of data provided by these repositories, we are interested in the exploitation of the full text content of scientific publications. Our aim is to bring new value to scientific publications by automatic extraction and semantic analysis. The identification of bibliographic references in texts makes it possible to localize specific text segments that carry linguistic markers in order to annotate a set of semantic categories related to citations. This work uses a categorization of surface linguistic markers organized in a linguistic ontology. The semantic annotations are used to enrich the document metadata and to provide new types of visualizations in an information retrieval context. We present the system architecture as well as some experimental results
@article{Bertin2012c, author = {Bertin, Marc and Atanassova, Iana}, title = {Semantic Enrichment of Scientific Publications and Metadata: Citation Analysis Through Contextual and Cognitive Analysis}, doi = {doi:10.1045/july2012-bertin}, issn = {1082-9873}, number = {7/8}, url = {https://www.dlib.org/dlib/july12/bertin/07bertin.html}, volume = {18}, author+an = {2=me}, journal = {D-Lib Magazine}, month = jul, year = {2012}, }

Conference Papers

Ordonnancement des réponses pour une recherche d’information sémantique à partir d’une ontologie discursive

Iana Atanassova, Marc Bertin, and Jean-Pierre Desclés

In Quatrième Atelier Recherche d’Information SEmantique (RISE 2012) co-located with 12^e Conférence Internationale Francophone sur l’Extraction et la Gestion des Connaissances (EGC 2012), Jan 2012

Bib

@inproceedings{Atanassova2012a,
  author = {Atanassova, Iana and Bertin, Marc and Descl{\'e}s, Jean-Pierre},
  booktitle = {{Quatri{\`e}me Atelier Recherche d'Information SEmantique (RISE 2012) co-located with 12<sup>e</sup> Conf{\'e}rence Internationale Francophone sur l'Extraction et la Gestion des Connaissances (EGC 2012)}},
  title = {{Ordonnancement des r{\'e}ponses pour une recherche d'information s{\'e}mantique {\`a} partir d'une ontologie discursive}},
  editor = {Catherine, Roussey and Jean-Pierre, Chevallet},
  address = {Bordeaux, France},
  author+an = {1=me},
  month = jan,
  year = {2012}
}

Outils de fouille textuelle à partir d’annotations sémantiques

Marc Bertin, Iana Atanassova, and Jean-Pierre Desclés

In 12^e Conférence Internationale Francophone sur l’Extraction et la Gestion des Connaissances (EGC 2012), Jan 2012

Bib

@inproceedings{Bertin2012,
  author = {Bertin, Marc and Atanassova, Iana and Descl{\'e}s, Jean-Pierre},
  booktitle = {{12<sup>e</sup> Conf{\'e}rence Internationale Francophone sur l'Extraction et la Gestion des Connaissances (EGC 2012)}},
  title = {{Outils de fouille textuelle {\`a} partir d'annotations s{\'e}mantiques}},
  subtitle = {Démonstration de logiciels},
  address = {Bordeaux, France},
  author+an = {2=me},
  month = jan,
  year = {2012}
}

Quelques applications de fouille textuelle dédiées aux articles scientifiques (démonstration)

Marc Bertin, Iana Atanassova, and Jean-Pierre Desclés

In 23^es Journées francophones d’ingénierie des connaissances (IC 2012), Jun 2012

Bib

@inproceedings{Bertin2012a,
  author = {Bertin, Marc and Atanassova, Iana and Descl{\'e}s, Jean-Pierre},
  booktitle = {{23<sup>es</sup> Journ{\'e}es francophones d'ing{\'e}nierie des connaissances (IC 2012)}},
  title = {{Quelques applications de fouille textuelle d{\'e}di{\'e}es aux articles scientifiques (d{\'e}monstration)}},
  address = {Paris, France},
  author+an = {2=me},
  month = jun,
  year = {2012}
}

Semantic Enrichment of Scientific Publications and Metadata

Marc Bertin and Iana Atanassova

In 1^st International Workshop on Mining Scientific Publications (WOSP 2012) co-located with ACM/IEEE Joint Conference on Digital Libraries (JCDL 2012), Jun 2012

Bib

@inproceedings{Bertin2012b,
  author = {Bertin, Marc and Atanassova, Iana},
  booktitle = {{1<sup>st</sup> International Workshop on Mining Scientific Publications (WOSP 2012) co-located with ACM/IEEE Joint Conference on Digital Libraries (JCDL 2012)}},
  title = {{Semantic Enrichment of Scientific Publications and Metadata}},
  organization = {{Petr Knoth and Zdenek Zdrahal and Andreas Juffinger}},
  address = {Washington DC, United States},
  author+an = {2=me},
  month = jun,
  year = {2012}
}

2011

Book Chapters

Fouille sémantique des thèses en ligne

Jean-Pierre Desclés, Florence Le Priol, Motasem Alrahabi, Iana Atanassova, and Marc Bertin

Jun 2011

Bib

@inbook{Descles2011,
  author = {Desclés, Jean-Pierre and Le Priol, Florence and Alrahabi, Motasem and Atanassova, Iana and Bertin, Marc},
  booktitle = {Traitement automatique des langues naturelles: de l'analyse à l'application (Cognition et traitement de l'information)},
  title = {{Fouille s{\'e}mantique des th{\`e}ses en ligne}},
  booksubtitle = {Recherche - Technologie - Applications (RTA)},
  editor = {Biskri, Ismaïl and Jebali, Adel},
  isbn = {9782746231382},
  pages = {77--108},
  publisher = {Hermes Science Publications},
  series = {Cognition et traitement de l'information},
  year = {2011},
  author+an = {4=me},
}

Miscellaneous

Recherche d’information et fouille textuelle à partir d’annotations sémantiques de textes scientifiques

Iana Atanassova

Nov 2011

Seminar. Laboratoire LIP6, UMR 7606 UPMC - CNRS, Paris

Bib

@misc{Atanassova2011,
  author = {Atanassova, Iana},
  title = {Recherche d'information et fouille textuelle à partir d'annotations sémantiques de textes scientifiques},
  note = {Seminar. Laboratoire LIP6, UMR 7606 UPMC - CNRS, Paris},
  author+an = {1=me},
  month = nov,
  year = {2011}
}

2010

Conference Papers

Fouille sémantique des thèses en ligne : un projet de Paris-Sorbonne

Jean-Pierre Desclés, Florence Le Priol, Motasem Alrahabi, Iana Atanassova, and Marc Bertin

In 78^e Congrès de l’ACFAS (Association francophone pour le savoir), ”Traitement automatique des langues naturelles, analyses et applications”, May 2010

Bib

@inproceedings{Descles2010,
  author = {Descl{\'e}s, Jean-Pierre and Le Priol, Florence and Alrahabi, Motasem and Atanassova, Iana and Bertin, Marc},
  booktitle = {78<sup>e</sup> Congr{\`e}s de l'ACFAS (Association francophone pour le savoir), ''Traitement automatique des langues naturelles, analyses et applications''},
  title = {{Fouille s{\'e}mantique des th{\`e}ses en ligne : un projet de Paris-Sorbonne}},
  address = {Montr{\'e}al, Canada},
  author+an = {4=me},
  keywords = {semantic search ; information retrieval ; contextual exploration ; thesis on line ; fouille s{\'e}mantique ; filtrage et recherche d'information ; exploration contextuelle ; th{\`e}se en ligne},
  month = may,
  year = {2010}
}

2009

Conference Papers

Automatic analysis of author judgment in scientific articles based on semantic annotation

Marc Bertin, Iana Atanassova, and Jean-Pierre Desclés

In The 22^nd International Florida Artificial Intelligence Research Society Conference, (FLAIRS 2009), May 2009

Bib

@inproceedings{Bertin2009,
  author = {Bertin, Marc and Atanassova, Iana and Descl{\'e}s, Jean-Pierre},
  booktitle = {{The 22<sup>nd</sup> International Florida Artificial Intelligence Research Society Conference, (FLAIRS 2009)}},
  title = {{Automatic analysis of author judgment in scientific articles based on semantic annotation}},
  publisher = {{AAAI Press}},
  address = {Sanibel Island, Florida, United States},
  author+an = {2=me},
  month = may,
  year = {2009}
}

Extraction of Authors’ Definitions using Indexed Reference Identification

Marc Bertin, Iana Atanassova, and Jean-Pierre Desclés

In Proceedings of the 1^st Workshop on Definition Extraction co-located with Recent Advances in Natural Language Processing (RANLP 2009), Sep 2009

Bib

@inproceedings{Bertin2009a,
  author = {Bertin, Marc and Atanassova, Iana and Descl{\'e}s, Jean-Pierre},
  booktitle = {{Proceedings of the 1<sup>st</sup> Workshop on Definition Extraction co-located with Recent Advances in Natural Language Processing (RANLP 2009)}},
  title = {{Extraction of Authors' Definitions using Indexed Reference Identification}},
  address = {Borovets, Bulgaria},
  author+an = {2=me},
  keywords = {indexed references ; definition extraction ; Semantic annotation},
  month = sep,
  year = {2009}
}

Miscellaneous

Quels outils de mesure et de navigation en sciences humaines et sociales ? Analyse sémantique et automatique de références bibliographiques

Iana Atanassova

Nov 2009

Seminar. Médialab, Sciences Po, Paris

Bib

@misc{Atanassova2009,
  author = {Atanassova, Iana},
  title = {Quels outils de mesure et de navigation en sciences humaines et sociales ? Analyse s\'emantique et automatique de r\'ef\'erences bibliographiques},
  note = {Seminar. M\'edialab, Sciences Po, Paris},
  author+an = {1=me},
  month = nov,
  year = {2009}
}

2008

Conference Papers

A Cross-lingual Approach to the Discourse Automatic Annotation: Application to French and Bulgarian

Iana Atanassova, Antoine Blais, and Jean-Pierre Desclés

In The 21^st International International Florida Artificial Intelligence Research Society Conference (FLAIRS 2008), May 2008

Abs Bib

In this paper we propose a cross-lingual approach to the discourse automatic annotation of scientific articles by the Contextual Exploration method. We present an application to French and Bulgarian as an illustration of the possibility to work with different languages that the method provides. We describe the methodology for the construction of the linguistic resources for Bulgarian based on the already existing resources for French and make an evaluation of the obtained annotations. We also discuss some of the applications of the discourse automatic annotation for automatic summarization and information retrieval.
@inproceedings{Atanassova2008, author = {Atanassova, Iana and Blais, Antoine and Descl{\'e}s, Jean-Pierre}, booktitle = {The 21st International International Florida Artificial Intelligence Research Society Conference (FLAIRS 2008)}, title = {{A Cross-lingual Approach to the Discourse Automatic Annotation: Application to French and Bulgarian}}, publisher = {AAAI Press}, address = {Coconut Grove, Florida, USA}, author+an = {1=me}, month = may, year = {2008} }

La plate-forme EXCOM comme outil automatique d’annotations sémantiques des textes pour la catégorisation des informations sur le Web

Iana Atanassova, Jean-Pierre Desclés, Aurélien Franchi, and Florence Le Priol

In Colloque "Internet : besoin de communiquer autrement", Université St. Clément d’Ohride, Oct 2008

Bib

@inproceedings{Atanassova2008a,
  author = {Atanassova, Iana and Descl\'es, Jean-Pierre and Franchi, Aur\'elien and Le Priol, Florence},
  booktitle = {Colloque "Internet : besoin de communiquer autrement", Universit\'e St. Cl\'ement d'Ohride},
  title = {{La plate-forme EXCOM comme outil automatique d'annotations s\'emantiques des textes pour la cat\'egorisation des informations sur le Web}},
  address = {Sofia, Bulgarie},
  author+an = {1=me},
  month = oct,
  year = {2008}
}

2007

Conference Papers

Discourse Automatic Annotation of Texts: an Application to Summarization

Antoine Blais, Iana Atanassova, Jean-Pierre Desclés, Leila Zighem, and Mimi Zhang

In The 20^th International Florida Artificial Intelligence Research Society Conference (FLAIRS 2007), May 2007

Abs Bib

The exploitation of the discourse structure of a text and the identification of the discourse categories are essential elements for the automatic summarization, as well as for the textual information retrieval. In this paper we will describe an automatic summarization strategy that uses these elements as the basis for the extraction of the most relevant textual segments that will constitute the summary. Certain linguistic markers allow us to annotate automatically a text according to discourse categories, in order to make visible the discourse structure and the discourse categories in the text. Our approach is domain independent and the discourse categories that we use for summarization are general for all natural languages. This makes it possible to apply our method to articles in various domains and in different languages.
@inproceedings{Blais2007, author = {Blais, Antoine and Atanassova, Iana and Descl\'es, Jean-Pierre and Zighem, Leila and Zhang, Mimi}, booktitle = {The 20th International Florida Artificial Intelligence Research Society Conference (FLAIRS 2007)}, title = {{Discourse Automatic Annotation of Texts: an Application to Summarization}}, publisher = {AAAI Press}, address = {Key West, Florida, USA}, author+an = {2=me}, month = may, year = {2007} }