On the Relation Between Fine-Tuning, Topological Properties, and Task Performance in Sense-Enhanced Embeddings.

Benoît Crabbé Deniz Ekin Yavas Timothée Bernard Benoît Crabbé Laura Kallmeyer On the Relation Between Fine-Tuning, Topological Properties, and Task Performance in Sense-Enhanced Embeddings. 23610-23625 2025 ACL (1) https://doi.org/10.18653/v1/2025.acl-long.1151 https://aclanthology.org/2025.acl-long.1151/ conf/acl/2025-1 db/conf/acl/acl2025-1.html#YavasBCK25 Sergei Bogdanov Alexandre Constantin Timothée Bernard Benoît Crabbé Étienne Bernard NuNER : Pré-entraînement d'un encodeur pour la reconnaissance d'entités nommées avec des données annotées automatiquement. 51-52 2025 TALN (2) https://aclanthology.org/2025.jeptalnrecital-trad.21/ conf/taln/2025-2 db/conf/taln/taln2025-2.html#BogdanovCBCB25 Nina Nusbaumer Guillaume Wisniewski Benoît Crabbé Évaluer la capacité des transformeurs à distinguer les significations compositionnelles et idiomatiques d'une même expression. 360-375 2025 TALN (1) https://aclanthology.org/2025.jeptalnrecital-taln.22/ conf/taln/2025-1 db/conf/taln/taln2025-1.html#NusbaumerWC25

Nathanaël Beau Benoît Crabbé RETROcode: Leveraging a Code Database for Improved Natural Language to Code Generation. 2025 April abs/2504.05759 CoRR https://doi.org/10.48550/arXiv.2504.05759 db/journals/corr/corr2504.html#abs-2504-05759 streams/journals/corr

Nathanaël Beau Benoît Crabbé CodeInsight: A Curated Dataset of Practical Coding Solutions from Stack Overflow. 5935-5947 2024 ACL (Findings) https://doi.org/10.18653/v1/2024.findings-acl.354 https://aclanthology.org/2024.findings-acl.354 conf/acl/2024f db/conf/acl/acl2024f.html#BeauC24 Sergei Bogdanov Alexandre Constantin Timothée Bernard Benoît Crabbé Etienne Bernard NuNER: Entity Recognition Encoder Pre-training via LLM-Annotated Data. 11829-11841 2024 EMNLP https://doi.org/10.18653/v1/2024.emnlp-main.660 https://aclanthology.org/2024.emnlp-main.660 conf/emnlp/2024 db/conf/emnlp/emnlp2024.html#BogdanovCBCB24 Deniz Yava Timothée Bernard Laura Kallmeyer Benoît Crabbé Improving Word Sense Induction through Adversarial Forgetting of Morphosyntactic Information. 238-251 2024 *SEM@NAACL https://doi.org/10.18653/v1/2024.starsem-1.19 conf/starsem/2024 db/conf/starsem/starsem2024.html#YavaBKC24

Sergei Bogdanov Alexandre Constantin Timothée Bernard Benoît Crabbé Etienne Bernard NuNER: Entity Recognition Encoder Pre-training via LLM-Annotated Data. 2024 abs/2402.15343 CoRR https://doi.org/10.48550/arXiv.2402.15343 db/journals/corr/corr2402.html#abs-2402-15343

Nathanaël Beau Benoît Crabbé CodeInsight: A Curated Dataset of Practical Coding Solutions from Stack Overflow. 2024 abs/2409.16819 CoRR https://doi.org/10.48550/arXiv.2409.16819 db/journals/corr/corr2409.html#abs-2409-16819 streams/journals/corr

Bingzhi Li Guillaume Wisniewski Benoît Crabbé Assessing the Capacity of Transformer to Abstract Syntactic Representations: A Contrastive Analysis Based on Long-distance Agreement. 18-33 2023 11 Trans. Assoc. Comput. Linguistics https://doi.org/10.1162/tacl_a_00531 db/journals/tacl/tacl11.html#LiWC23

Bingzhi Li Guillaume Wisniewski Benoît Crabbé How Distributed are Distributed Representations? An Observation on the Locality of Syntactic Information in Verb Agreement Tasks. 501-507 2022 ACL (2) https://doi.org/10.18653/v1/2022.acl-short.54 https://aclanthology.org/2022.acl-short.54 conf/acl/2022-2 db/conf/acl/acl2022-2.html#LiWC22 Nathanaël Beau Benoît Crabbé The impact of lexical and grammatical processing on generating code from natural language. 2204-2214 2022 ACL (Findings) https://doi.org/10.18653/v1/2022.findings-acl.173 https://aclanthology.org/2022.findings-acl.173 conf/acl/2022f db/conf/acl/acl2022f.html#BeauC22 Loïc Grobol Mathilde Regnault Pedro Javier Ortiz Suárez Benoît Sagot Laurent Romary Benoît Crabbé BERTrade: Using Contextual Embeddings to Parse Old French. 1104-1113 2022 LREC https://aclanthology.org/2022.lrec-1.119 conf/lrec/2022 db/conf/lrec/lrec2022.html#GrobolRSSRC22 Antoine Simoulin Benoît Crabbé Unifying Parsing and Tree-Structured Models for Generating Sentence Semantic Representations. 267-276 2022 NAACL-HLT (Student Research Workshop) https://doi.org/10.18653/v1/2022.naacl-srw.33 https://aclanthology.org/2022.naacl-srw.33 conf/naacl/2022s db/conf/naacl/naacl2022s.html#SimoulinC22 Bingzhi Li Guillaume Wisniewski Benoît Crabbé Les représentations distribuées sont-elles vraiment distribuées ? Observations sur la localisation de l'information syntaxique dans les tâches d'accord du verbe en français (How Distributed are Distributed Representations ? An Observation on the Locality of Syntactic). 384-391 2022 TALN-RECITAL https://aclanthology.org/2022.jeptalnrecital-taln.38 conf/taln/2022-1 db/conf/taln/taln2022-1.html#LiWC22

Nathanaël Beau Benoît Crabbé The impact of lexical and grammatical processing on generating code from natural language. 2022 abs/2202.13972 CoRR https://arxiv.org/abs/2202.13972 db/journals/corr/corr2202.html#abs-2202-13972

Bingzhi Li Guillaume Wisniewski Benoît Crabbé Assessing the Capacity of Transformer to Abstract Syntactic Representations: A Contrastive Analysis Based on Long-distance Agreement. 2022 abs/2212.04523 CoRR https://doi.org/10.48550/arXiv.2212.04523 db/journals/corr/corr2212.html#abs-2212-04523

Antoine Simoulin Benoît Crabbé How Many Layers and Why? An Analysis of the Model Depth in Transformers. 221-228 2021 ACL (student) https://doi.org/10.18653/v1/2021.acl-srw.23 https://aclanthology.org/2021.acl-srw.23 conf/acl/2021-s db/conf/acl/acl2021-s.html#SimoulinC21 Antoine Simoulin Benoît Crabbé Contrasting distinct structured views to learn sentence embeddings. 71-79 2021 EACL (Student Research Workshop) https://doi.org/10.18653/v1/2021.eacl-srw.11 https://aclanthology.org/2021.eacl-srw.11/ conf/eacl/2021-s db/conf/eacl/eacl2021-s.html#SimoulinC21 Bingzhi Li Guillaume Wisniewski Benoît Crabbé Are Transformers a Modern Version of ELIZA? Observations on French Object Verb Agreement. 4599-4610 2021 EMNLP (1) https://doi.org/10.18653/v1/2021.emnlp-main.377 https://aclanthology.org/2021.emnlp-main.377 conf/emnlp/2021-1 db/conf/emnlp/emnlp2021-1.html#LiWC21 Loïc Grobol Benoît Crabbé Analyse en dépendances du français avec des plongements contextualisés (French dependency parsing with contextualized embeddings). 106-114 2021 TALN (1) https://aclanthology.org/2021.jeptalnrecital-taln.9 conf/taln/2021-1 db/conf/taln/taln2021-1.html#GrobolC21 Antoine Simoulin Benoît Crabbé Un modèle Transformer Génératif Pré-entrainé pour le______ français (Generative Pre-trained Transformer in______ (French) We introduce a French adaptation from the well-known GPT model). 246-255 2021 TALN (1) https://aclanthology.org/2021.jeptalnrecital-taln.24 conf/taln/2021-1 db/conf/taln/taln2021-1.html#SimoulinC21

Yair Lakretz Theo Desbordes Jean-Rémi King Benoît Crabbé Maxime Oquab Stanislas Dehaene Can RNNs learn Recursive Nested Subject-Verb Agreements? 2021 abs/2101.02258 CoRR https://arxiv.org/abs/2101.02258 db/journals/corr/corr2101.html#abs-2101-02258

Bingzhi Li Guillaume Wisniewski Benoît Crabbé Are Transformers a Modern Version of ELIZA? Observations on French Object Verb Agreement. 2021 abs/2109.10133 CoRR https://arxiv.org/abs/2109.10133 db/journals/corr/corr2109.html#abs-2109-10133

Hang Le 0001 Loïc Vial Jibril Frej Vincent Segonne Maximin Coavoux Benjamin Lecouteux Alexandre Allauzen Benoît Crabbé Laurent Besacier Didier Schwab FlauBERT: Unsupervised Language Model Pre-training for French. 2479-2490 2020 LREC https://aclanthology.org/2020.lrec-1.302/ conf/lrec/2020 db/conf/lrec/lrec2020.html#LeVFSCLACBS20 Lucie Barque Pauline Haas Richard Huyghe Delphine Tribout Marie Candito Benoît Crabbé Vincent Segonne FrSemCor: Annotating a French Corpus with Supersenses. 5912-5918 2020 LREC https://aclanthology.org/2020.lrec-1.724/ conf/lrec/2020 db/conf/lrec/lrec2020.html#BarqueHHTCCS20 Hang Le 0001 Loïc Vial Jibril Frej Vincent Segonne Maximin Coavoux Benjamin Lecouteux Alexandre Allauzen Benoît Crabbé Laurent Besacier Didier Schwab FlauBERT : des modèles de langue contextualisés pré-entraînés pour le français (FlauBERT : Unsupervised Language Model Pre-training for French). 268-278 2020 JEP-TALN-RECITAL (2) https://aclanthology.org/2020.jeptalnrecital-taln.26/ conf/taln/2020-2 db/conf/taln/taln2020-2.html#LeVFSCLACBS20

Maximin Coavoux Benoît Crabbé Shay B. Cohen Unlexicalized Transition-based Discontinuous Constituency Parsing. 73-89 2019 7 Trans. Assoc. Comput. Linguistics https://doi.org/10.1162/tacl_a_00255 https://www.wikidata.org/entity/Q128037677 db/journals/tacl/tacl7.html#CoavouxCC19

Benoît Crabbé Murielle Fabre Christophe Pallier Variable beam search for generative neural parsing and its relevance for the analysis of neuro-imaging signal. 1150-1160 2019 EMNLP/IJCNLP (1) https://doi.org/10.18653/v1/D19-1106 conf/emnlp/2019-1 db/conf/emnlp/emnlp2019-1.html#CrabbeFP19 Vincent Segonne Marie Candito Benoît Crabbé Using Wiktionary as a resource for WSD : the case of French verbs. 259-270 2019 IWCS (1) https://doi.org/10.18653/v1/w19-0422 https://aclanthology.org/W19-0422/ conf/iwcs/2019-1 db/conf/iwcs/iwcs2019-1.html#SegonneCC19

Maximin Coavoux Benoît Crabbé Shay B. Cohen Unlexicalized Transition-based Discontinuous Constituency Parsing. 2019 abs/1902.08912 CoRR http://arxiv.org/abs/1902.08912 db/journals/corr/corr1902.html#abs-1902-08912

Hang Le 0001 Loïc Vial Jibril Frej Vincent Segonne Maximin Coavoux Benjamin Lecouteux Alexandre Allauzen Benoît Crabbé Laurent Besacier Didier Schwab FlauBERT: Unsupervised Language Model Pre-training for French. 2019 abs/1912.05372 CoRR http://arxiv.org/abs/1912.05372 db/journals/corr/corr1912.html#abs-1912-05372

Maximin Coavoux Benoît Crabbé Multilingual Lexicalized Constituency Parsing with Word-Level Auxiliary Tasks. 331-336 2017 EACL (2) https://doi.org/10.18653/v1/e17-2053 https://aclanthology.org/E17-2053/ conf/eacl/2017-2 db/conf/eacl/eacl2017-2.html#CrabbeC17a Maximin Coavoux Benoît Crabbé Incremental Discontinuous Phrase Structure Parsing with the GAP Transition. 1259-1270 2017 EACL (1) https://doi.org/10.18653/v1/e17-1118 https://aclanthology.org/E17-1118/ conf/eacl/2017-1 db/conf/eacl/eacl2017-1.html#CrabbeC17 Maximin Coavoux Benoît Crabbé Représentation et analyse automatique des discontinuités syntaxiques dans les corpus arborés en constituants du français (Representation and parsing of syntactic discontinuities in French constituent treebanks). 77-92 2017 TALN https://aclanthology.org/2017.jeptalnrecital-long.6/ conf/taln/2017 db/conf/taln/taln2017.html#CoavouxC17

Maximin Coavoux Benoît Crabbé Prédiction structurée pour l'analyse syntaxique en constituants par transitions : modèles denses et modèles creux. 2016 57 Trait. Autom. des Langues 1 http://atala.org/Prediction-structuree-pour-l db/journals/tal/tal57.html#CoavouxC16

Maximin Coavoux Benoît Crabbé Neural Greedy Constituent Parsing with Dynamic Oracles. 2016 ACL (1) https://doi.org/10.18653/v1/p16-1017 https://aclanthology.org/P16-1017/ conf/acl/2016-1 db/conf/acl/acl2016-1.html#CoavouxC16 Rachel Bawden Benoît Crabbé Boosting for Efficient Model Selection for Syntactic Parsing. 1-11 2016 COLING https://aclanthology.org/C16-1001/ conf/coling/2016 db/conf/coling/coling2016.html#BawdenC16 Kristina Gulordava Paola Merlo Benoît Crabbé Dependency length minimisation effects in short spans: a large-scale analysis of adjective placement in complex noun phrases. 477-482 2015 ACL (2) https://doi.org/10.3115/v1/p15-2078 https://aclanthology.org/P15-2078/ conf/acl/2015-2 db/conf/acl/acl2015-2.html#GulordavaMC15 Benoît Crabbé Multilingual discriminative lexicalized phrase structure parsing. 1847-1856 2015 EMNLP https://doi.org/10.18653/v1/d15-1212 https://aclanthology.org/D15-1212/ conf/emnlp/2015 db/conf/emnlp/emnlp2015.html#Crabbe15 Maximin Coavoux Benoît Crabbé Comparaison d'architectures neuronales pour l'analyse syntaxique en constituants. 291-302 2015 TALN (long papers) https://aclanthology.org/2015.jeptalnrecital-long.25/ conf/taln/2015-l db/conf/taln/taln2015-l.html#CoavouxC15 Benoît Crabbé An LR-inspired generalized lexicalized phrase structure parser. 541-552 2014 COLING https://aclanthology.org/C14-1052/ conf/coling/2014 db/conf/coling/coling2014.html#Crabbe14 Benoît Crabbé A discriminative parser of the LR family for phrase structure parsing (Un analyseur discriminant de la famille LR pour l'analyse en constituants) [in French]. 328-339 2014 TALN (1) https://aclanthology.org/F14-1029/ conf/taln/2014-1 db/conf/taln/taln2014-1.html#Crabbe14

Benoît Crabbé Denys Duchier Claire Gardent Joseph Le Roux Yannick Parmentier 0001 XMG: eXtensible MetaGrammar. 591-629 2013 39 Comput. Linguistics 3 https://doi.org/10.1162/COLI_a_00144 db/journals/coling/coling39.html#CrabbeDGRP13

Anne Abeillé Benoît Crabbé Towards a treebank of spoken French (Vers un treebank du français parlé) [in French]. 174-187 2013 TALN (1) https://aclanthology.org/F13-1013/ conf/taln/2013-1 db/conf/taln/taln2013-1.html#AbeilleC13 Djamé Seddah Marie Candito Benoît Crabbé Enrique Henestroza Anguiano Ubiquitous Usage of a Broad Coverage French Corpus: Processing the Est Republicain corpus. 3249-3254 2012 LREC http://www.lrec-conf.org/proceedings/lrec2012/summaries/1130.html conf/lrec/2012 db/conf/lrec/lrec2012.html#SeddahCCA12 Luc Boruta Sharon Peperkamp Benoît Crabbé Emmanuel Dupoux Testing the Robustness of Online Word Segmentation: Effects of Linguistic Diversity and Phonetic Variation. 1-9 2011 CMCL@ACL https://aclanthology.org/W11-0601/ conf/acl-cmcl/2011 db/conf/acl-cmcl/acl-cmcl2011.html#BorutaPCD11 Marie Candito Benoît Crabbé Pascal Denis Statistical French Dependency Parsing: Treebank Conversion and First Results. 2010 LREC http://www.lrec-conf.org/proceedings/lrec2010/summaries/392.html conf/lrec/2010 db/conf/lrec/lrec2010.html#CanditoCD10 Juliette Thuilier Gwendoline Fox Benoît Crabbé Approche quantitative en syntaxe : l'exemple de l'alternance de position de l'adjectif épithète en français. 71-80 2010 TALN (Articles longs) https://aclanthology.org/2010.jeptalnrecital-long.8/ conf/taln/2010-1 db/conf/taln/taln2010-1.html#ThuilierFC10 Marie Candito Benoît Crabbé Improving generative statistical parsing with semi-supervised word clustering. 138-141 2009 IWPT https://aclanthology.org/W09-3821/ conf/iwpt/2009 db/conf/iwpt/iwpt2009.html#CanditoC09 Djamé Seddah Marie Candito Benoît Crabbé Cross parser evaluation : a French Treebanks study. 150-161 2009 IWPT https://aclanthology.org/W09-3824/ conf/iwpt/2009 db/conf/iwpt/iwpt2009.html#SeddahCC09 Djamé Seddah Marie Candito Benoît Crabbé Adaptation de parsers statistiques lexicalisés pour le français : Une évaluation complète sur corpus arborés. 1-10 2009 TALN (Articles courts) https://aclanthology.org/2009.jeptalnrecital-court.1/ conf/taln/2009-2 db/conf/taln/taln2009-2.html#SeddahCC09 Marie Candito Benoît Crabbé Pascal Denis François Guérin Analyse syntaxique du français : des constituants aux dépendances. 31-40 2009 TALN (Articles longs) https://aclanthology.org/2009.jeptalnrecital-long.4/ conf/taln/2009-1 db/conf/taln/taln2009-1.html#CanditoCDG09 Benoît Crabbé Marie Candito Expériences d'analyse syntaxique statistique du français. 161-170 2008 TALN (Articles longs) https://aclanthology.org/2008.jeptalnrecital-long.17/ conf/taln/2008-1 db/conf/taln/taln2008-1.html#CrabbeC08 Yannick Parmentier 0001 Joseph Le Roux Benoît Crabbé XMG - An Expressive Formalism for Describing Tree-Based Grammars. 2006 conf/eacl/2006 EACL https://aclanthology.org/E06-2005/ db/conf/eacl/eacl2006.html#ParmentierRC06 Joseph Le Roux Benoît Crabbé Yannick Parmentier 0001 A Constraint Driven Metagrammar. 9-16 2006 TAG https://aclanthology.org/W06-1502/ conf/tag/2006 db/conf/tag/tag2006.html#RouxCP06 Benoît Crabbé Grammatical Development with Xmg. 84-100 2005 conf/lacl/2005 LACL https://doi.org/10.1007/11422532_6 db/conf/lacl/lacl2005.html#Crabbe05 Benoît Crabbé Projection et monotonie dans un langage de représentation lexico-grammatical. 427-432 2005 TALN (Articles courts) https://aclanthology.org/2005.jeptalnrecital-court.8/ conf/taln/2005-2 db/conf/taln/taln2005-2.html#Crabbe05 Benoît Crabbé Denys Duchier Metagrammar Redux. 32-47 2004 conf/cslp/2004 CSLP https://doi.org/10.1007/11424574_3 db/conf/cslp/cslp2004.html#CrabbeD04 Benoît Crabbé Bertrand Gaiffe Azim Roussanaly Une plate-forme de conception et d'exploitation d'une grammaire d'arbres adjoints lexicalisés. 75-84 2003 TALN (Articles longs) https://aclanthology.org/2003.jeptalnrecital-long.6/ conf/taln/2003-1 db/conf/taln/taln2003-1.html#CrabbeGR03 Bertrand Gaiffe Benoît Crabbé Azim Roussanaly A new metagrammar compiler. 234-241 2002 TAG+ https://aclanthology.org/W02-2233/ conf/tag/2002 db/conf/tag/tag2002.html#GaiffeCR02 Anne Abeillé Alexandre Allauzen Enrique Henestroza Anguiano Lucie Barque Rachel Bawden Nathanaël Beau Etienne BernardÉtienne Bernard Timothée Bernard Laurent Besacier Sergei Bogdanov Luc Boruta Marie Candito Maximin Coavoux Shay B. Cohen Alexandre Constantin Stanislas Dehaene Pascal Denis Theo Desbordes Denys Duchier Emmanuel Dupoux Murielle Fabre Gwendoline Fox Jibril Frej Bertrand Gaiffe Claire Gardent Loïc Grobol François GuerinFrançois Guérin Kristina Gulordava Pauline Haas Richard Huyghe Laura Kallmeyer Jean-Rémi King Yair Lakretz Hang Le 0001 Benjamin Lecouteux Bingzhi Li Paola Merlo Nina Nusbaumer Maxime Oquab Christophe Pallier Yannick Parmentier 0001 Sharon Peperkamp Mathilde Regnault Laurent Romary Azim Roussanaly Joseph Le Roux Benoît Sagot Didier Schwab Djamé Seddah Vincent Segonne Antoine Simoulin Pedro Ortiz SuarezPedro Javier Ortiz Suárez Juliette Thuilier Delphine Tribout Loïc Vial Guillaume Wisniewski Deniz Yava Deniz Ekin Yavas