🔬 Works of Centre National de la Recherche Scientifique

83 works · the most cited first · ← Centre National de la Recherche Scientifique

1. SciPy 1.0 — Fundamental Algorithms for Scientific Computing in PythonPauli Virtanen, Ralf Gommers, Travis E. Oliphant, et al.2019 · 38,317 citations
2. Emerging Properties in Self-Supervised Vision TransformersMathilde Caron, Hugo Touvron, Ishan Misra, et al.2021 · 5,910 citations
3. Twitter as a Corpus for Sentiment Analysis and Opinion MiningAlexander Pak, Patrick Paroubek2010 · 2,905 citations
4. SemEval-2016 Task 5: Aspect Based Sentiment AnalysisMaria Pontiki, Dimitris Galanis, Haris Papageorgiou, et al.2016 · 1,656 citations
5. Optuna: A Next-generation Hyperparameter Optimization FrameworkTakuya Akiba, Shotaro Sano, Toshihiko Yanase, et al.2019 · 1,246 citations
6. Assessing the Ability of LSTMs to Learn Syntax-Sensitive DependenciesTal Linzen, Emmanuel Dupoux, Yoav Goldberg2016 · 1,239 citations
7. Findings of the 2016 Conference on Machine TranslationOndřej Bojar, Rajen Chatterjee, Christian Federmann, et al.2016 · 936 citations
8. Unsupervised Machine Translation Using Monolingual Corpora OnlyGuillaume Lample, Alexis Conneau, Ludovic Denoyer, et al.2017 · 650 citations
9. The WebNLG Challenge: Generating Text from RDF DataClaire Gardent, Anastasia Shimorina, Shashi Narayan, et al.2017 · 579 citations
10. Creating Training Corpora for NLG Micro-PlannersClaire Gardent, Anastasia Shimorina, Shashi Narayan, et al.2017 · 526 citations
11. SPLADE: Sparse Lexical and Expansion Model for First Stage RankingThibault Formal, Benjamin Piwowarski, Stéphane Clinchant2021 · 510 citations
12. BioMistral: A Collection of Open-Source Pretrained Large Language Models for Medical DomainsYanis Labrak, Adrien Bazoge, Emmanuel Morin, et al.2024 · 406 citations
13. QuestEval: Summarization Asks for Fact-based EvaluationThomas Scialom, Paul-Alexis Dray, Sylvain Lamprier, et al.2021 · 353 citations
14. Survey: Multiword Expression Processing: A SurveyMathieu Constant, Gülşen Eryiǧit, Johanna Monti, et al.2017 · 296 citations
15. FlauBERT: Unsupervised Language Model Pre-training for FrenchHang Le, Loïc Vial, Jibril Frej, et al.2019 · 293 citations
16. Evaluating Discourse Phenomena in Neural Machine TranslationRachel Bawden, Rico Sennrich, Alexandra Birch, et al.2017 · 252 citations
17. Humanity's Last ExamLong Phan, Alice Gatti, Ziwen Han, et al.2025 · 235 citations
18. Modeling Language Variation and Universals: A Survey on Typological Linguistics for Natural Language ProcessingEdoardo Maria Ponti, Helen O'Horan, Yevgeni Berzak, et al.2019 · 217 citations
19. Answers Unite! Unsupervised Metrics for Reinforced Summarization ModelsThomas Scialom, Sylvain Lamprier, Benjamin Piwowarski, et al.2019 · 210 citations
20. Discourse Structure and Dialogue Acts in Multiparty Dialogue: the STAC CorpusNicholas Asher, Julie Hunter, Mathieu Morey, et al.2016 · 202 citations
21. GLiNER: Generalist Model for Named Entity Recognition using Bidirectional TransformerUrchade Zaratiana, Nadi Tomeh, Pierre Holat, et al.2024 · 189 citations
22. The 2020 Bilingual, Bi-Directional WebNLG+ Shared Task: Overview and Evaluation Results (WebNLG+ 2020)Thiago Castro Ferreira, Claire Gardent, Nikolai Ilinykh, et al.2020 · 163 citations
23. REFINER: Reasoning Feedback on Intermediate RepresentationsDebjit Paul, Mete Ismayilzada, Maxime Peyrard, et al.2023 · 152 citations
24. SUD or Surface-Syntactic Universal Dependencies: An annotation scheme near-isomorphic to UDKim Gerdes, Bruno Guillaume, Sylvain Kahane, et al.2018 · 144 citations
25. How much progress have we made on RST discourse parsing? A replication study of recent results on the RST-DTMathieu Morey, Philippe Muller, Nicholas Asher2017 · 124 citations
26. GlotLID: Language Identification for Low-Resource LanguagesAmir Hossein Kargaran, Ayyoob Imani, François Yvon, et al.2023 · 115 citations
27. MLSUM: The Multilingual Summarization CorpusThomas Scialom, Paul-Alexis Dray, Sylvain Lamprier, et al.2020 · 114 citations
28. French CrowS-Pairs: Extending a challenge dataset for measuring social bias in masked language models to a language other than EnglishAurélie Névéol, Yoann Dupont, Julien Bezançon, et al.2022 · 107 citations
29. Constrained Decoding for Text-Level Discourse ParsingPhilippe Muller, Stergos Afantenos, Pascal Denis, et al.2012 · 99 citations
30. Discourse parsing for multi-party chat dialoguesStergos Afantenos, Eric Kow, Nicholas Asher, et al.2015 · 97 citations
31. Get that into your head: Tigre vowel harmonies as templaticNoam Faust2017 · 89 citations
32. Towards a Contextual Pragmatic Model to Detect Irony in TweetsJihen Karoui, Farah Benamara Zitoune, Véronique Moriceau, et al.2015 · 81 citations
33. A Dependency Perspective on RST Discourse Parsing and EvaluationMathieu Morey, Philippe Muller, Nicholas Asher2018 · 76 citations
34. Unsupervised Sentence Simplification Using Deep SemanticsShashi Narayan, Claire Gardent2016 · 76 citations
35. Integer Linear Programming for Discourse ParsingJérémy Perret, Stergos Afantenos, Nicholas Asher, et al.2016 · 71 citations
36. Exploring the Impact of Pragmatic Phenomena on Irony Detection in Tweets: A Multilingual Corpus StudyJihen Karoui, Farah Benamara, Véronique Moriceau, et al.2017 · 69 citations
37. Findings of the WMT 2017 Biomedical Translation Shared TaskAntonio Jimeno Yepes, Aurélie Névéol, Mariana Neves, et al.2017 · 69 citations
38. Developing a French FrameNet: Methodology and First resultsMarie Candito, Pascal Amsili, Lucie Barque, et al.2014 · 63 citations
39. Annotation Guidelines for Questions under Discussion and Information StructureArndt Riester, Lisa Brunetti, Kordula De Kuthy2018 · 49 citations
40. The DISRPT 2021 Shared Task on Elementary Discourse Unit Segmentation, Connective Detection, and Relation ClassificationAmir Zeldes, Yang Janet Liu, Mikel Iruskieta, et al.2021 · 49 citations
41. The DISRPT 2023 Shared Task on Elementary Discourse Unit Segmentation, Connective Detection, and Relation ClassificationChloé Braud, Yang Janet Liu, Eleni Metheniti, et al.2023 · 37 citations
42. Pattern-and-root inflectional morphology: the Arabic broken pluralAlexis Amid Neme, Eric Laporte2026 · 36 citations
43. Improving Surface-syntactic Universal Dependencies (SUD): MWEs and deep syntactic featuresKim Gerdes, Bruno Guillaume, Sylvain Kahane, et al.2019 · 30 citations
44. The ISO Standard for Dialogue Act Annotation, Second EditionHarry Bunt, Volha Petukhova, Emer Gilmartin, et al.2020 · 29 citations
45. Fixing Translation Divergences in Parallel Corpora for Neural MTMinhQuang Pham, Josep Crego, Jean Senellart, et al.2018 · 24 citations
46. Multilingual Irony Detection with Dependency Syntax and Neural ModelsAlessandra Teresa Cignarella, Valerio Basile, Manuela Sanguinetti, et al.2020 · 21 citations
47. Learning Scalar Adjective Intensity from ParaphrasesAnne Cocos, Skyler Wharton, Ellie Pavlick, et al.2018 · 21 citations
48. Syntactic annotation of spontaneous speech: application to call-center conversation dataThierry Bazillon, Melanie Deplano, Frederic Bechet, et al.2012 · 20 citations
49. Annotation guidelines of UD and SUD treebanks for spoken corpora: A proposalSylvain Kahane, Bernard Caron, Emmett Strickland, et al.2021 · 16 citations
50. Restoring Arabic vowels through omission-tolerant dictionary lookupAlexis Amid Neme, Sebastien Paumier2019 · 12 citations
51. Discourse Relation Prediction and Discourse Parsing in Dialogues with Minimal SupervisionChuyuan Li, Chloé Braud, Maxime Amblard, et al.2024 · 12 citations
52. Errator: a Tool to Help Detect Annotation Errors in the Universal Dependencies ProjectGuillaume Wisniewski2018 · 12 citations
53. Experimental detection of vowel pronunciation variants in AmharicThomas Pellegrini, Lori Lamel2006 · 11 citations
54. LIMSI@CoNLL'17: UD Shared TaskLauriane Aufrant, Guillaume Wisniewski, François Yvon2017 · 10 citations
55. An Error Analysis Framework for Shallow Surface RealizationAnastasia Shimorina, Yannick Parmentier, Claire Gardent2021 · 8 citations
56. Exponence, allomorphy and haplology in the number and State morphology of Modern HebrewNoam Faust2018 · 7 citations
57. Gender exponence and apparent polarity in a class of Omani Mehri pluralsRadwa Fathi2017 · 6 citations
58. Graph Rewriting for Enhanced Universal DependenciesBruno Guillaume, Guy Perrier2021 · 6 citations
59. Cross-lingual and Supervised Models for Morphosyntactic Annotation: a Comparison on RomanianLauriane Aufrant, Guillaume Wisniewski, François Yvon2016 · 5 citations
60. Exclaiming non-sententially: exclamative sluices and the (non-elliptical) nature of ellipsis constructionsJonathan Ginzburg, Jong-Bok Kim2023 · 5 citations
61. The Syriac grammatical tradition as an «extension» of Greek grammar: the parts of speech and the participle (La tradition grammaticale syriaque comme « extension » de la grammaire grecque. Les parties du discours et le participe)Margherita Farina2021 · 4 citations
62. In the LLM era, Word Sense Induction remains unsolvedAnna Mosolova, Marie Candito, Carlos Ramisch2025 · 4 citations
63. Neural Lemmatization of Multiword ExpressionsMarine Schmitt, Mathieu Constant2019 · 4 citations
64. A Falta de Pan, Buenas Son Tortas: The Efficacy of Predicted UPOS Tags for Low Resource UD ParsingMark Anderson, Mathieu Dehouck, Carlos Gómez-Rodríguez2021 · 3 citations
65. Automatically Selecting the Best Dependency Annotation Design with Dynamic OraclesGuillaume Wisniewski, Ophélie Lacroix, François Yvon2018 · 2 citations
66. Unravelling Indirect Answers to Wh-Questions: Corpus Construction, Analysis, and GenerationZulipiye Yusupujiang, Jonathan Ginzburg2023 · 2 citations
67. Bidirectionnal converter between syntactic annotations : from French Treebank Dependencies to PASSAGE annotations, and backMunshi Asadullah, Patrick Paroubek, Anne Vilnat2014 · 1 citation
68. Potential of ASR for the study of L2 learner corporaSarra El Ayari, Zhongjie Li2024 · 1 citation
69. A Classifier of Word-Level Variants in Witnesses of Biblical Hebrew ManuscriptsIglika Nikolova-Stoupak, Maxime Amblard, Sophie Robert-Hayek, et al.2025 · 1 citation
70. Parallel Corpora of Scholarly Documents for English-French Machine TranslationZiqian Peng, Lichao Zhu, Rachel Bawden, et al.2026 · 1 citation
71. THIVLVC: Retrieval Augmented Dependency Parsing for LatinLuc Pommeret, Thibault Wagret, Jules Deret2026 · 1 citation
72. Sema System for the DMR 2026 Shared Task: Multistage UMR Parsing with Qwen3-4BRémi de Vergnette, Maxime Amblard2026 · 1 citation
73. BEReshiT: an Ancient Hebrew Model based on DictaBERTIglika Nikolova-Stoupak, Maxime Amblard, Frédérique Rey2026
74. Stem Configurations, Lexical Items, and Phonological Words in MalteseGilbert Puech2023
75. Evaluating the Retrieval Component in a Retrieval-Augmented Summarization System for Patient Records in FrenchMarco Naguib, Christel Gérardin, Victor Beaucoté, et al.2026
76. EIFFEL: a novel benchmark to measure bias of English heavy training on French idiomatic expressionsCharlotte Noel, Nicholas Asher, Olivier Gouvert, et al.2026
77. Automatic Extraction of Textual and Phonemic Complexity for French Cued SpeechMagali Norré, Brigitte Bigi, Núria Gala, et al.2026
78. SagaQA: A Multi-hop Reasoning Benchmark for Long-form Narrative Understanding in TV SeriesGalann Pennec, Zhengyuan Liu, Nicholas Asher, et al.2026
79. Detecting Experiential Intertextuality Across Migration Routes: Beyond Surface Similarity in French NarrativesSakayo Toadoum Sari, Nelly Robin, Michelle Auzanneau, et al.2026
80. Translation from the Information Bottleneck Perspective: an Efficiency Analysis of Spatial Prepositions in BitextsAntoine Taroni, Ludovic Moncla, Frederique Laforest2026
81. A Proposal for a More Universal Annotation of Relative Clauses in Universal DependenciesSantiago Herrera, Sylvain Kahane2026
82. Extracting First Order Logic formulas from graphical semantic representationsRémi de Vergnette, Vincent Tourneur, Maxime Amblard2026
83. From Latents to Labels: Zero-Shot Named Entity Recognition using Sparse Autoencoder FeaturesNakanyseth Vuth, Gilles Sérasset, Didier Schwab2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/labs/centre-national-de-la-recherche-scientifique/works/