Florian Boudin


2024

pdf bib
Automatically Suggesting Diverse Example Sentences for L2 Japanese Learners Using Pre-Trained Language Models
Enrico Benedetti | Akiko Aizawa | Florian Boudin
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)

Providing example sentences that are diverse and aligned with learners’ proficiency levels is essential for fostering effective language acquisition.This study examines the use of Pre-trained Language Models (PLMs) to produce example sentences targeting L2 Japanese learners.We utilize PLMs in two ways: as quality scoring components in a retrieval system that draws from a newly curated corpus of Japanese sentences, and as direct sentence generators using zero-shot learning.We evaluate the quality of sentences by considering multiple aspects such as difficulty, diversity, and naturalness, with a panel of raters consisting of learners of Japanese, native speakers – and GPT-4.Our findings suggest that there is inherent disagreement among participants on the ratings of sentence qualities, except for difficulty. Despite that, the retrieval approach was preferred by all evaluators, especially for beginner and advanced target proficiency, while the generative approaches received lower scores on average.Even so, our experiments highlight the potential for using PLMs to enhance the adaptability of sentence suggestion systems and therefore improve the language learning journey.

pdf bib
CASIMIR: A Corpus of Scientific Articles Enhanced with Multiple Author-Integrated Revisions
Léane Jourdan | Florian Boudin | Nicolas Hernandez | Richard Dufour
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)

Writing a scientific article is a challenging task as it is a highly codified and specific genre, consequently proficiency in written communication is essential for effectively conveying research findings and ideas. In this article, we propose an original textual resource on the revision step of the writing process of scientific articles. This new dataset, called CASIMIR, contains the multiple revised versions of 15,646 scientific articles from OpenReview, along with their peer reviews. Pairs of consecutive versions of an article are aligned at sentence-level while keeping paragraph location information as metadata for supporting future revision studies at the discourse level. Each pair of revised sentences is enriched with automatically extracted edits and associated revision intention. To assess the initial quality on the dataset, we conducted a qualitative study of several state-of-the-art text revision approaches and compared various evaluation metrics. Our experiments led us to question the relevance of the current evaluation methods for the text revision task.

2023

pdf bib
Actes de CORIA-TALN 2023. Actes de l'atelier "Analyse et Recherche de Textes Scientifiques" (ARTS)@TALN 2023
Florian Boudin | Béatrice Daille | Richard Dufour | Oumaima El | Maël Houbre | Léane Jourdan | Nihel Kooli
Actes de CORIA-TALN 2023. Actes de l'atelier "Analyse et Recherche de Textes Scientifiques" (ARTS)@TALN 2023

pdf bib
Projet NaviTerm : navigation terminologique pour une montée en compétence rapide et personnalisée sur un domaine de recherche
Florian Boudin | Richard Dufour | Béatrice Daille
Actes de CORIA-TALN 2023. Actes de l'atelier "Analyse et Recherche de Textes Scientifiques" (ARTS)@TALN 2023

Cet article présente le projet NaviTerm dont l’objectif est d’accélérer la montée en compétence des chercheurs sur un domaine de recherche par la création automatique de représentations terminologiques synthétiques et navigables des connaissances scientifiques.

pdf bib
Classification de relation pour la génération de mots-clés absents
Maël Houbre | Florian Boudin | Béatrice Daille
Actes de CORIA-TALN 2023. Actes de l'atelier "Analyse et Recherche de Textes Scientifiques" (ARTS)@TALN 2023

Les modèles encodeur-décodeur constituent l’état de l’art en génération de mots-clés. Cependant, malgré de nombreuses adaptations de cette architecture, générer des mots-clés absents du texte du document est toujours une tâche difficile. Cette étude montre qu’entraîner au préalable un modèle sur une tâche de classification de relation entre un document et un mot-clé, permet d’améliorer la génération de mots-clés absents.

pdf bib
CASIMIR : un Corpus d’Articles Scientifiques Intégrant les ModIfications et Révisions des auteurs
Léane Jourdan | Florian Boudin | Richard Dufour | Nicolas Hernandez
Actes de CORIA-TALN 2023. Actes de l'atelier "Analyse et Recherche de Textes Scientifiques" (ARTS)@TALN 2023

Écrire un article scientifique est une tâche difficile. L’écriture scientifique étant un genre très codifié, de bonnes compétences d’écriture sont essentielles pour transmettre ses idées et les résultats de ses recherches. Cet article décrit les motivations et les travaux préliminaires de la création du corpus CASIMIR dont l’objectif est d’offrir une ressource sur l’étape de révision du processus d’écriture d’un article scientifique. CASIMIR est un corpus des multiples versions de 26 355 articles scientifiques provenant d’OpenReview accompagné des relectures par les pairs.

2022

pdf bib
Cross-lingual and Cross-domain Transfer Learning for Automatic Term Extraction from Low Resource Data
Amir Hazem | Merieme Bouhandi | Florian Boudin | Beatrice Daille
Proceedings of the Thirteenth Language Resources and Evaluation Conference

Automatic Term Extraction (ATE) is a key component for domain knowledge understanding and an important basis for further natural language processing applications. Even with persistent improvements, ATE still exhibits weak results exacerbated by small training data inherent to specialized domain corpora. Recently, transformers-based deep neural models, such as BERT, have proven to be efficient in many downstream NLP tasks. However, no systematic evaluation of ATE has been conducted so far. In this paper, we run an extensive study on fine-tuning pre-trained BERT models for ATE. We propose strategies that empirically show BERT’s effectiveness using cross-lingual and cross-domain transfer learning to extract single and multi-word terms. Experiments have been conducted on four specialized domains in three languages. The obtained results suggest that BERT can capture cross-domain and cross-lingual terminologically-marked contexts shared by terms, opening a new design-pattern for ATE.

pdf bib
A Large-Scale Dataset for Biomedical Keyphrase Generation
Maël Houbre | Florian Boudin | Beatrice Daille
Proceedings of the 13th International Workshop on Health Text Mining and Information Analysis (LOUHI)

Keyphrase generation is the task consisting in generating a set of words or phrases that highlight the main topics of a document. There are few datasets for keyphrase generation in the biomedical domain and they do not meet the expectations in terms of size for training generative models. In this paper, we introduce kp-biomed, the first large-scale biomedical keyphrase generation dataset collected from PubMed abstracts. We train and release several generative models and conduct a series of experiments showing that using large scale datasets improves significantly the performances for present and absent keyphrase generation. The dataset and models are available online.

2021

pdf bib
Redefining Absent Keyphrases and their Effect on Retrieval Effectiveness
Florian Boudin | Ygor Gallina
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Neural keyphrase generation models have recently attracted much interest due to their ability to output absent keyphrases, that is, keyphrases that do not appear in the source text. In this paper, we discuss the usefulness of absent keyphrases from an Information Retrieval (IR) perspective, and show that the commonly drawn distinction between present and absent keyphrases is not made explicit enough. We introduce a finer-grained categorization scheme that sheds more light on the impact of absent keyphrases on scientific document retrieval. Under this scheme, we find that only a fraction (around 20%) of the words that make up keyphrases actually serves as document expansion, but that this small fraction of words is behind much of the gains observed in retrieval effectiveness. We also discuss how the proposed scheme can offer a new angle to evaluate the output of neural keyphrase generation models.

2020

pdf bib
TermEval 2020: TALN-LS2N System for Automatic Term Extraction
Amir Hazem | Mérieme Bouhandi | Florian Boudin | Beatrice Daille
Proceedings of the 6th International Workshop on Computational Terminology

Automatic terminology extraction is a notoriously difficult task aiming to ease effort demanded to manually identify terms in domain-specific corpora by automatically providing a ranked list of candidate terms. The main ways that addressed this task can be ranged in four main categories: (i) rule-based approaches, (ii) feature-based approaches, (iii) context-based approaches, and (iv) hybrid approaches. For this first TermEval shared task, we explore a feature-based approach, and a deep neural network multitask approach -BERT- that we fine-tune for term extraction. We show that BERT models (RoBERTa for English and CamemBERT for French) outperform other systems for French and English languages.

pdf bib
An Evaluation Dataset for Identifying Communicative Functions of Sentences in English Scholarly Papers
Kenichi Iwatsuki | Florian Boudin | Akiko Aizawa
Proceedings of the Twelfth Language Resources and Evaluation Conference

Formulaic expressions, such as ‘in this paper we propose’, are used by authors of scholarly papers to perform communicative functions; the communicative function of the present example is ‘stating the aim of the paper’. Collecting such expressions and pairing them with their communicative functions would be highly valuable for various tasks, particularly for writing assistance. However, such collection and paring in a principled and automated manner would require high-quality annotated data, which are not available. In this study, we address this shortcoming by creating a manually annotated dataset for detecting communicative functions in sentences. Starting from a seed list of labelled formulaic expressions, we retrieved new sentences from scholarly papers in the ACL Anthology and asked multiple human evaluators to label communicative functions. To show the usefulness of our dataset, we conducted a series of experiments that determined to what extent sentence representations acquired by recent models, such as word2vec and BERT, can be employed to detect communicative functions in sentences.

pdf bib
Keyphrase Generation for Scientific Document Retrieval
Florian Boudin | Ygor Gallina | Akiko Aizawa
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

Sequence-to-sequence models have lead to significant progress in keyphrase generation, but it remains unknown whether they are reliable enough to be beneficial for document retrieval. This study provides empirical evidence that such models can significantly improve retrieval performance, and introduces a new extrinsic evaluation framework that allows for a better understanding of the limitations of keyphrase generation models. Using this framework, we point out and discuss the difficulties encountered with supplementing documents with -not present in text- keyphrases, and generalizing models across domains. Our code is available at https://github.com/boudinfl/ir-using-kg

2019

pdf bib
DeFT 2019 : Auto-encodeurs, Gradient Boosting et combinaisons de modèles pour l’identification automatique de mots-clés. Participation de l’équipe TALN du LS2N (Autoencoders, gradient boosting and ensemble systems for automatic keyphrase assignment : The LS2N team participation’s in the 2019 edition of DeFT)
Mérième Bouhandi | Florian Boudin | Ygor Gallina
Actes de la Conférence sur le Traitement Automatique des Langues Naturelles (TALN) PFIA 2019. Défi Fouille de Textes (atelier TALN-RECITAL)

Nous présentons dans cet article la participation de l’équipe TALN du LS2N à la tâche d’indexation de cas cliniques (tâche 1). Nous proposons deux systèmes permettant d’identifier, dans la liste de mots-clés fournie, les mots-clés correspondant à un couple cas clinique/discussion, ainsi qu’un classifieur entraîné sur la combinaison des sorties des deux systèmes. Nous présenterons dans le détail les descripteurs utilisés pour représenter les mots-clés ainsi que leur impact sur nos systèmes de classification.

pdf bib
KPTimes: A Large-Scale Dataset for Keyphrase Generation on News Documents
Ygor Gallina | Florian Boudin | Beatrice Daille
Proceedings of the 12th International Conference on Natural Language Generation

Keyphrase generation is the task of predicting a set of lexical units that conveys the main content of a source text. Existing datasets for keyphrase generation are only readily available for the scholarly domain and include non-expert annotations. In this paper we present KPTimes, a large-scale dataset of news texts paired with editor-curated keyphrases. Exploring the dataset, we show how editors tag documents, and how their annotations differ from those found in existing datasets. We also train and evaluate state-of-the-art neural keyphrase generation models on KPTimes to gain insights on how well they perform on the news domain. The dataset is available online at https://github.com/ygorg/KPTimes.

2018

pdf bib
Unsupervised Keyphrase Extraction with Multipartite Graphs
Florian Boudin
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)

We propose an unsupervised keyphrase extraction model that encodes topical information within a multipartite graph structure. Our model represents keyphrase candidates and topics in a single graph and exploits their mutually reinforcing relationship to improve candidate ranking. We further introduce a novel mechanism to incorporate keyphrase selection preferences into the model. Experiments conducted on three widely used datasets show significant improvements over state-of-the-art graph-based models.

2016

pdf bib
Modélisation unifiée du document et de son domaine pour une indexation par termes-clés libre et contrôlée (Unified document and domain-specific model for keyphrase extraction and assignment )
Adrien Bougouin | Florian Boudin | Beatrice Daille
Actes de la conférence conjointe JEP-TALN-RECITAL 2016. volume 2 : TALN (Articles longs)

Dans cet article, nous nous intéressons à l’indexation de documents de domaines de spécialité par l’intermédiaire de leurs termes-clés. Plus particulièrement, nous nous intéressons à l’indexation telle qu’elle est réalisée par les documentalistes de bibliothèques numériques. Après analyse de la méthodologie de ces indexeurs professionnels, nous proposons une méthode à base de graphe combinant les informations présentes dans le document et la connaissance du domaine pour réaliser une indexation (hybride) libre et contrôlée. Notre méthode permet de proposer des termes-clés ne se trouvant pas nécessairement dans le document. Nos expériences montrent aussi que notre méthode surpasse significativement l’approche à base de graphe état de l’art.

pdf bib
How Document Pre-processing affects Keyphrase Extraction Performance
Florian Boudin | Hugo Mougard | Damien Cram
Proceedings of the 2nd Workshop on Noisy User-generated Text (WNUT)

The SemEval-2010 benchmark dataset has brought renewed attention to the task of automatic keyphrase extraction. This dataset is made up of scientific articles that were automatically converted from PDF format to plain text and thus require careful preprocessing so that irrevelant spans of text do not negatively affect keyphrase extraction performance. In previous work, a wide range of document preprocessing techniques were described but their impact on the overall performance of keyphrase extraction models is still unexplored. Here, we re-assess the performance of several keyphrase extraction models and measure their robustness against increasingly sophisticated levels of document preprocessing.

pdf bib
TermITH-Eval: a French Standard-Based Resource for Keyphrase Extraction Evaluation
Adrien Bougouin | Sabine Barreaux | Laurent Romary | Florian Boudin | Béatrice Daille
Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16)

Keyphrase extraction is the task of finding phrases that represent the important content of a document. The main aim of keyphrase extraction is to propose textual units that represent the most important topics developed in a document. The output keyphrases of automatic keyphrase extraction methods for test documents are typically evaluated by comparing them to manually assigned reference keyphrases. Each output keyphrase is considered correct if it matches one of the reference keyphrases. However, the choice of the appropriate textual unit (keyphrase) for a topic is sometimes subjective and evaluating by exact matching underestimates the performance. This paper presents a dataset of evaluation scores assigned to automatically extracted keyphrases by human evaluators. Along with the reference keyphrases, the manual evaluations can be used to validate new evaluation measures. Indeed, an evaluation measure that is highly correlated to the manual evaluation is appropriate for the evaluation of automatic keyphrase extraction methods.

pdf bib
Keyphrase Annotation with Graph Co-Ranking
Adrien Bougouin | Florian Boudin | Béatrice Daille
Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers

Keyphrase annotation is the task of identifying textual units that represent the main content of a document. Keyphrase annotation is either carried out by extracting the most important phrases from a document, keyphrase extraction, or by assigning entries from a controlled domain-specific vocabulary, keyphrase assignment. Assignment methods are generally more reliable. They provide better-formed keyphrases, as well as keyphrases that do not occur in the document. But they are often silent on the contrary of extraction methods that do not depend on manually built resources. This paper proposes a new method to perform both keyphrase extraction and keyphrase assignment in an integrated and mutual reinforcing manner. Experiments have been carried out on datasets covering different domains of humanities and social sciences. They show statistically significant improvements compared to both keyphrase extraction and keyphrase assignment state-of-the art methods.

pdf bib
pke: an open source python-based keyphrase extraction toolkit
Florian Boudin
Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: System Demonstrations

We describe pke, an open source python-based keyphrase extraction toolkit. It provides an end-to-end keyphrase extraction pipeline in which each component can be easily modified or extented to develop new approaches. pke also allows for easy benchmarking of state-of-the-art keyphrase extraction approaches, and ships with supervised models trained on the SemEval-2010 dataset.

2015

pdf bib
Concept-based Summarization using Integer Linear Programming: From Concept Pruning to Multiple Optimal Solutions
Florian Boudin | Hugo Mougard | Benoit Favre
Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing

pdf bib
LINA: Identifying Comparable Documents from Wikipedia
Emmanuel Morin | Amir Hazem | Florian Boudin | Elizaveta Loginova-Clouet
Proceedings of the Eighth Workshop on Building and Using Comparable Corpora

pdf bib
Reducing Over-generation Errors for Automatic Keyphrase Extraction using Integer Linear Programming
Florian Boudin
Proceedings of the ACL 2015 Workshop on Novel Computational Approaches to Keyphrase Extraction

2014

pdf bib
TopicRank : ordonnancement de sujets pour l’extraction automatique de termes-clés [TopicRank: topic ranking for automatic key-term extraction]
Adrien Bougouin | Florian Boudin
Traitement Automatique des Langues, Volume 55, Numéro 1 : Varia [Varia]

pdf bib
The impact of domains for Keyphrase extraction (Influence des domaines de spécialité dans l’extraction de termes-clés) [in French]
Adrien Bougouin | Florian Boudin | Béatrice Daille
Proceedings of TALN 2014 (Volume 1: Long Papers)

2013

pdf bib
Keyphrase Extraction for N-best Reranking in Multi-Sentence Compression
Florian Boudin | Emmanuel Morin
Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

pdf bib
Construction of a Free Large Part-of-Speech Annotated Corpus in French (Construction d’un large corpus écrit libre annoté morpho-syntaxiquement en français) [in French]
Nicolas Hernandez | Florian Boudin
Proceedings of TALN 2013 (Volume 1: Long Papers)

pdf bib
TALN Archives : a digital archive of French research articles in Natural Language Processing (TALN Archives : une archive numérique francophone des articles de recherche en Traitement Automatique de la Langue) [in French]
Florian Boudin
Proceedings of TALN 2013 (Volume 2: Short Papers)

pdf bib
Proceedings of RECITAL 2013
Florian Boudin | Loïc Barrault
Proceedings of RECITAL 2013

pdf bib
TopicRank: Graph-Based Topic Ranking for Keyphrase Extraction
Adrien Bougouin | Florian Boudin | Béatrice Daille
Proceedings of the Sixth International Joint Conference on Natural Language Processing

pdf bib
A Comparison of Centrality Measures for Graph-Based Keyphrase Extraction
Florian Boudin
Proceedings of the Sixth International Joint Conference on Natural Language Processing

2012

pdf bib
Détection et correction automatique d’erreurs d’annotation morpho-syntaxique du French TreeBank (Detecting and Correcting POS Annotation in the French TreeBank) [in French]
Florian Boudin | Nicolas Hernandez
Proceedings of the Joint Conference JEP-TALN-RECITAL 2012, volume 2: TALN

pdf bib
Participation du LINA à DEFT2012 (LINA at DEFT2012) [in French]
Florian Boudin | Amir Hazem | Nicolas Hernandez | Prajol Shrestha
JEP-TALN-RECITAL 2012, Workshop DEFT 2012: DÉfi Fouille de Textes (DEFT 2012 Workshop: Text Mining Challenge)

2011

pdf bib
Utilisation d’un score de qualité de traduction pour le résumé multi-document cross-lingue (Using translation quality scores for cross-language multi-document summarization)
Stéphane Huet | Florian Boudin | Juan-Manuel Torres-Moreno
Actes de la 18e conférence sur le Traitement Automatique des Langues Naturelles. Articles longs

Le résumé automatique cross-lingue consiste à générer un résumé rédigé dans une langue différente de celle utilisée dans les documents sources. Dans cet article, nous proposons une approche de résumé automatique multi-document, basée sur une représentation par graphe, qui prend en compte des scores de qualité de traduction lors du processus de sélection des phrases. Nous évaluons notre méthode sur un sous-ensemble manuellement traduit des données utilisées lors de la campagne d’évaluation internationale DUC 2004. Les résultats expérimentaux indiquent que notre approche permet d’améliorer la lisibilité des résumés générés, sans pour autant dégrader leur informativité.

2010

pdf bib
Positional Language Models for Clinical Information Retrieval
Florian Boudin | Jian-Yun Nie | Martin Dawes
Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing

pdf bib
Clinical Information Retrieval using Document and PICO Structure
Florian Boudin | Jian-Yun Nie | Martin Dawes
Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics

2009

pdf bib
Résumé automatique multi-document et indépendance de la langue : une première évaluation en français
Florian Boudin | Juan-Manuel Torres-Moreno
Actes de la 16ème conférence sur le Traitement Automatique des Langues Naturelles. Articles courts

Le résumé automatique de texte est une problématique difficile, fortement dépendante de la langue et qui peut nécessiter un ensemble de données d’apprentissage conséquent. L’approche par extraction peut aider à surmonter ces difficultés. (Mihalcea, 2004) a démontré l’intérêt des approches à base de graphes pour l’extraction de segments de texte importants. Dans cette étude, nous décrivons une approche indépendante de la langue pour la problématique du résumé automatique multi-documents. L’originalité de notre méthode repose sur l’utilisation d’une mesure de similarité permettant le rapprochement de segments morphologiquement proches. De plus, c’est à notre connaissance la première fois que l’évaluation d’une approche de résumé automatique multi-document est conduite sur des textes en français.

2008

pdf bib
A Scalable MMR Approach to Sentence Scoring for Multi-Document Update Summarization
Florian Boudin | Marc El-Bèze | Juan-Manuel Torres-Moreno
Coling 2008: Companion volume: Posters