Guillaume Wisniewski
Présentation
Publications
Publications
|
|
Beyond Surprisal: A Dual Metric Framework for Lexical Skill Acquisition in LLMsProceedings of the 31st International Conference on Computational Linguistics (COLING 2025), Jan 2025, Abu Dhabi, United Arab Emirates. pp.6636-6641 |
|
|
Testing LLMs' Capabilities in Annotating Translations Based on an Error Typology Designed for LSP Translation: First Experiments with ChatGPT20th Machine Translation Summit XX Volume 1, Jun 2025, Genève, Switzerland. pp.190-203 |
Using Automatic Speech Recognition to put the interactive back into the corpus of ThulungTalking Data conference, University of Bologna, Oct 2025, Bologna, Italy |
|
First steps using ASR on Thulung: the importance of text typesInternational Conference on Sino-Tibetan Languages and Linguistics, University of Bern, Sep 2025, Bern, Switzerland |
|
|
|
Évaluer la capacité des transformeurs à distinguer les significations compositionnelles et idiomatiques d'une même expression20e Conférence en Recherche d’Information et Applications (CORIA) 32ème Conférence sur le Traitement Automatique des Langues Naturelles (TALN) 27ème Rencontre des Étudiants Chercheurs en Informatique pour le Traitement Automatique des Langues (RECITAL) Les 18e Rencontres Jeunes Chercheurs en RI (RJCRI), 2025, Marseille, France. pp.360-375 |
|
|
Mesure du niveau de proximité entre enregistrements audio et évaluation indirecte du niveau d’abstraction des représentations issues d’un grand modèle de langage35èmes Journées d'Études sur la Parole (JEP 2024), Jul 2024, Toulouse, France. pp.112-121 |
|
|
Gender and language identification in Multilingual Models of Speech: exploring the genericity and robustness of speech representationsInterspeech 2024, Sep 2024, Kos Island, Greece. pp.3330-3334, ⟨10.21437/Interspeech.2024-953⟩ |
|
|
Establishing degrees of closeness between audio recordings along different dimensions using large-scale cross-lingual modelsFindings of the Association for Computational Linguistics: EACL 2024, Association for Computational Linguistics, Mar 2024, St. Julian’s, Malta |
|
|
Évaluation de la Similarité Textuelle : Entre Sémantique et Surface dans les Représentations Neuronales35èmes Journées d'Études sur la Parole (JEP 2024) 31ème Conférence sur le Traitement Automatique des Langues Naturelles (TALN 2024) 26ème Rencontre des Étudiants Chercheurs en Informatique pour le Traitement Automatique des Langues (RECITAL 2024), Jul 2024, Toulouse, France. pp.85-96 |
|
|
Multi-way Variational NMT for UGC: Improving Robustness in Zero-shot Scenarios via Mixture Density NetworksNoDaLiDa 2023 - 24th Nordic Conference on Computational Linguistics, May 2023, Torshavn, Faroe Islands |
|
|
Investigating techniques for a deeper understanding of Neural Machine Translation (NMT) systems through data filtering and fine-tuning strategies8th World Machine Translation, Association for Computational Linguistics, Dec 2023, Singapore (SG), Singapore. pp.275-281 |
|
|
Fine-tuning mBART50 with French and Farsi data to improve the translation of Farsi dislocations into English and FrenchMachine Translation Summit 2023, University of Macau; NLP2CT lab, University of Macau; AAMT; MACETS, Sep 2023, Macau SAR, China. pp.152-161 |
|
|
Using Artificial French Data to Understand the Emergence of Gender Bias in Transformer Language ModelsProceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, Dec 2023, Singapore, France. pp.10362-10371, ⟨10.18653/v1/2023.emnlp-main.641⟩ |
|
|
From 'snippet-lects' to doculects and dialects: Leveraging neural representations of speech for placing audio signals in a language landscape2nd Annual Meeting of the Special Interest Group on Under-resourced Languages (SIGUL 2023), a satellite workshop of Interspeech 2023, Aug 2023, Dublin, Ireland. pp.29-33, ⟨10.21437/SIGUL.2023-7⟩ |
|
|
Faciliter l'accès des praticiens du Traitement Automatique des Langues à des jeux de données de langues rares : un deuxième point d'étapeJournées Jointes des Groupements de Recherche Linguistique Informatique, Formelle et de Terrain (LIFT) et Traitement Automatique des Langues (TAL), Nov 2022, Marseille, France |
|
|
Understanding the Impact of UGC Specificities on Translation QualityW-NUT 2021 - Seventh Workshop on Noisy User-generated Text (colocated with EMNLP 2021), association for computational linguistics, Nov 2021, Punta Cana, Dominican Republic. pp.189-198, ⟨10.18653/v1/2021.wnut-1.22⟩ |
|
|
Les représentations distribuées sont-elles vraiment distribuées ? Observations sur la localisation de l'information syntaxique dans les tâches d'accord du verbe en françaisTraitement Automatique des Langues Naturelles, 2022, Avignon, France. pp.384-391 |
|
|
Is the Language Familiarity Effect gradual ? A computational modelling approachCogSci 2022 - 44th Annual Meeting of the Cognitive Science Society, Jul 2022, Toronto, Canada |
|
|
Investigating the usefulness of i-vectors for automatic language characterizationSpeech Prosody 2022 - 11th International Conference on Speech Prosody, May 2022, Lisbonne, Portugal. ⟨10.21437/speechprosody.2022-94⟩ |
|
|
Fine-tuning pre-trained models for Automatic Speech Recognition: experiments on a fieldwork corpus of Japhug (Trans-Himalayan family)ComputEL-5 5th Workshop on Computational Methods for Endangered Languages (ComputEL-5), May 2022, Dublin, Ireland. ⟨10.18653/v1/2022.computel-1.21⟩ |
|
|
Plugging a neural phoneme recognizer into a simple language model: a workflow for low-resource settingsInterspeech 2022 - 23rd Annual Conference of the International Speech Communication Association, Sep 2022, Incheon, South Korea. pp.4905-4909, ⟨10.21437/Interspeech.2022-11314⟩ |
|
|
Facilitating NLP specialists’ access to language archive materials: an updateJournées Jointes des Groupements de Recherche Linguistique Informatique, Formelle et de Terrain (LIFT) et Traitement Automatique des Langues (TAL), Nov 2022, Marseille, France. pp.109-118 |
|
|
Flux d'informations dans les systèmes encodeur-décodeur. Application à l'explication des biais de genre dans les systèmes de traduction automatique.Traitement Automatique des Langues Naturelles, Jun 2022, Avignon, France. pp.10-18 |
|
|
La robustesse de la traduction neuronale : les systèmes de traduction automatique neuronale à l' épreuve de la reproductibilité de l'expérienceJournée d'étude "Robustesse des systemes de TAL", Nov 2022, Paris, France |
|
|
Analyzing Gender Translation Errors to Identify Information Flows between the Encoder and Decoder of a NMT SystemBlackboxNLP 2022, Dec 2022, Abu Dhabi, United Arab Emirates |
|
|
How Distributed are Distributed Representations? An Observation on the Locality of Syntactic Information in Verb Agreement Tasks60th Annual Meeting of the Association for Computational Linguistics, May 2022, Dublin, Ireland. pp.501-507, ⟨10.18653/v1/2022.acl-short.54⟩ |
|
|
Toward a Test Set of Dislocations in Persian for Neural Machine TranslationThe Third International Workshop on NLP Solutions for Under Resourced Languages (NSURL 2022), Dec 2022, Trente, Italy |
|
|
Les modèles pré-entraînés à l'épreuve des langues rares : expériences de reconnaissance de mots sur la langue japhug (sino-tibétain)JEP 2022 - 34e Journées d’Études sur la Parole, Jun 2022, Noirmoutier, France. ⟨10.21437/JEP.2022-52⟩ |
|
|
Probing phoneme, language and speaker information in unsupervised speech representationsInterspeech 2022 - 23rd INTERSPEECH Conference, Sep 2022, Incheon, South Korea |
|
|
The SPECTRANS System Description for the WMT22 Biomedical Task2022 Seventh Conference on Machine Translation (WMT22), Association for Computational Linguistics, Dec 2022, Abu Dhabi, France. pp.895-900 |
|
|
Déterminer la similarité entre deux langues à l'aide des modèles pré-entraînés de la parole. Une étude piloteJournées Jointes des Groupements de Recherche Linguistique Informatique, Formelle et de Terrain (LIFT) et Traitement Automatique des Langues (TAL), Nov 2022, Marseille, France. pp.67-73 |
|
|
User-friendly automatic transcription of low-resource languages: Plugging ESPnet into ElpisComputEL-4: Fourth Workshop on the Use of Computational Methods in the Study of Endangered Languages, Mar 2021, Hawai‘i, United States |
|
|
Nonlinear optimal control using deep reinforcement learning9th IUTAM Symposium on Laminar-Turbulent Transition (IUTAM transition 2019), IUTAM – International Union of Theoretical and Applied Mechanics, Sep 2019, London, United Kingdom. pp.279-290, ⟨10.1007/978-3-030-67902-6_24⟩ |
|
|
The SPECTRANS System Description for the WMT21 Terminology TaskEMNLP 2021 SIXTH CONFERENCE ON MACHINE TRANSLATION (WMT21), ACL, Nov 2021, Punta Cana, Dominican Republic. pp.815-820 |
|
|
Spécialisation de modèles neuronaux pour la transcription phonémique : premiers pas vers la reconnaissance de mots pour les langues raresJournées scientifiques du Groupement de recherche "Linguistique informatique, formelle et de terrain" (GDR LIFT), Dec 2021, Grenoble, France |
|
|
Are Neural Networks Extracting Linguistic Properties or Memorizing Training Data? An Observation with a Multilingual Probe for Predicting TenseEACL 2021, Apr 2021, Kiev (on line), Ukraine |
|
|
Are Transformers a Modern Version of ELIZA? Observations on French Object Verb Agreement2021 Conference on Empirical Methods in Natural Language Processing, Nov 2021, Punta Cana, Dominican Republic. ⟨10.18653/v1/2021.emnlp-main.377⟩ |
|
|
Natural Language Processing for language documentation: a progress report for Japhug and NaSixth Workshop on Sino-Tibetan Languages of Southwest China 2021, Sep 2021, Kobe, Japan |
|
|
Screening Gender Transfer in Neural Machine TranslationFourth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP, Association for computational linguistics, Nov 2021, Punta Cana, Dominica |
|
|
Biais de genre dans un système de traduction automatique neuronale : une étude préliminaireTraitement Automatique des Langues Naturelles, 2021, Lille, France. pp.11-25 |
|
|
Deux corpus audio transcrits de langues rares (japhug et na) normalisés en vue d'expériences en traitement du signalJournées scientifiques du Groupement de recherche "Linguistique informatique, formelle et de terrain" (GDR LIFT), Dec 2021, Grenoble, France |
|
|
Noisy UGC Translation at the Character Level: Revisiting Open-Vocabulary Capabilities and Robustness of Char-Based ModelsW-NUT 2021 - 7th Workshop on Noisy User-generated Text (colocated with EMNLP 2021), Association for computational linguistics, Nov 2021, Punta Cana, Dominican Republic. pp.199-211, ⟨10.18653/v1/2021.wnut-1.23⟩ |
|
|
Apprentissage automatique pour la surveillance de marquesConférence Nationale sur les Applications Pratiques de l’Intelligence Artificielle, Jun 2021, Saint-Etienne, France |
|
|
Phonemic transcription of low-resource languages: To what extent can preprocessing be automated?1st Joint SLTU (Spoken Language Technologies for Under-resourced languages) and CCURL (Collaboration and Computing for Under-Resourced Languages) Workshop, 2020, Marseille, France. pp.306-315 |
|
|
Analyse d'erreurs de transcriptions phonémiques automatiques d'une langue « rare » : le na (mosuo)6e conférence conjointe Journées d'Études sur la Parole (JEP, 33e édition), Traitement Automatique des Langues Naturelles (TALN, 27e édition), Rencontre des Étudiants Chercheurs en Informatique pour le Traitement Automatique des Langues (RÉCITAL, 22e édition). Volume 1 : Journées d'Études sur la Parole, Jun 2020, Nancy, France. pp.451-462 |
|
|
Ouvrir aux linguistes « de terrain » un accès à la transcription automatique2èmes journées scientifiques du Groupement de Recherche Linguistique Informatique Formelle et de Terrain (LIFT), 2020, Montrouge, France. pp.83-94 |
Control of a chaotic dynamical system with a Deep Reinforcement Learning approach90th GAMM Annual Meeting, Feb 2019, Vienna, Austria |
|
|
|
A Comparison between NMT and PBSMT Performance for Translating Noisy User-Generated ContentThe 22nd Nordic Conference on Computational Linguistics (NoDaLiDa’19), Sep 2019, Turku, Finland |
|
|
Combien d'exemples de tests sont-ils nécessaires à une évaluation fiable~? Quelques observations sur l'évaluation de l'analyse morphosyntaxique du français.26e Conférence sur le Traitement Automatique des Langues Naturelles, 2019, Toulouse, France. pp.215-222 |
|
|
How Bad are PoS Tagger in Cross-Corpora Settings? Evaluating Annotation Divergence in the UD Project2019 Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Association for Computational Linguistics, Jun 2019, Minneapolis, Minnesota, United States. pp.218 - 227 |
Apprentissage d’un modèle dynamique chaotique par un LSTMConférence sur l’Apprentissage automatique (CAp), Jul 2019, Toulouse, France |
|
|
|
Automated Paraphrase Lattice Creation for HyTER Machine Translation EvaluationConference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Association for Computational Linguistics Jun 2018, Nouvelle Orléans, United States. pp.480 - 485, ⟨10.18653/v1/N18-2077⟩ |
|
|
Automatically Selecting the Best Dependency Annotation Design with Dynamic OraclesConference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Association for Computational Linguistics, Jun 2018, New Orleans, United States. pp.401 - 406, ⟨10.18653/v1/N18-2064⟩ |
Control-oriented model learning with a recurrent neural network71st Annual APS/DFD Meeting, Nov 2018, Atlanta, United States |
|
|
|
Quantifying training challenges of dependency parsersInternational Conference on Computational Linguistics, Aug 2018, Santa Fe, New Mexico, United States. pp.3191 - 3202 |
|
|
Low-latency speaker spotting with online diarization and detectionOdyssey 2018: The Speaker and Language Recognition Workshop, ISCA, Jun 2018, Les Sables d'Olonne, France. ⟨10.21437/Odyssey.2018-20⟩ |
Errator: a Tool to Help Detect Annotation Errors in the Universal Dependencies ProjectEleventh International Conference on Language Resources and Evaluation, May 2018, Miyazaki, Japan |
|
|
|
Divergences entre annotations dans le projet Universal Dependencies et leur impact sur l'évaluation de l'étiquetage morpho-syntaxiqueConférence sur le Traitement Automatique des Langues Naturelles, May 2018, Rennes, France |
|
|
Exploiting Dynamic Oracles to Train Projective Dependency Parsers on Non-Projective TreesConference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, ACL, Jun 2018, New Orleans, United States. pp.413 - 419, ⟨10.18653/v1/N18-2066⟩ |
|
|
Don't Stop Me Now! Using Global Dynamic Oracles to Correct Training Biases of Transition-Based Dependency ParsersConference of the European Chapter of the ACL, Jan 2017, Valencia, Spain. pp.318 - 323, ⟨10.18653/v1/E17-2051⟩ |
|
|
Adaptation au domaine pour l'analyse morpho-syntaxiqueConférence sur le Traitement Automatique des Langues Naturelles, Jun 2017, Orléans, France |
|
|
A Systematic Comparison of Syntactic Representations of Dependency ParsingProceedings of the NoDaLiDa 2017 Workshop on Universal Dependencies (UDW 2017), May 2017, Gothenburg, Sweden |
|
|
LIMSI@CoNLL'17: UD Shared TaskConference on Computational Natural Language Learning, Association for computational linguistics, Aug 2017, Vancouver, Canada. pp.163-173, ⟨10.18653/v1/K17-3017⟩ |
|
|
Cross-lingual Dependency Transfer : What Matters? Assessing the Impact of Pre- and Post-processingWorkshop on Multilingual and Cross-lingual Methods in NLP, Jun 2016, San Diego, United States. pp.20 - 29, ⟨10.18653/v1/W16-1203⟩ |
|
|
Cross-lingual alignment transfer: a chicken-and-egg story?Workshop on Multilingual and Cross-lingual Methods in NLP , Jun 2016, San Diego, CA, United States. pp.35-44, ⟨10.18653/v1/W16-1205⟩ |
|
|
LIMSI@WMT16: Machine Translation of NewsFirst Conference on Machine Translation, Aug 2016, Berlin, Germany. pp.239--245, ⟨10.18653/v1/W16-2304⟩ |
|
|
Investigating gender adaptation for speech translation23ème Conférence sur le Traitement Automatique des Langues Naturelles, Jul 2016, Paris, France. pp.490-497 |
|
|
Zero-resource Dependency Parsing: Boosting Delexicalized Cross-lingual Transfer with Linguistic KnowledgeCOLING 2016, the 26th International Conference on Computational Linguistics, 2016, Osaka, Japan. pp.119--130 |
|
|
Oublier ce qu'on sait, pour mieux apprendre ce qu'on ne sait pas : une étude sur les contraintes de type dans les modèles CRFConférence sur le Traitement Automatique des Langues Naturelles, ATALA, 2015, Caen, France |
|
|
Why Predicting Post-Edition is so Hard? Failure Analysis of LIMSI Submission to the APE Shared TaskTenth Workshop on Statistical Machine Translation, Association for Computational Linguistics, Sep 2015, Lisbon, Portugal. pp.222 - 227 |
|
|
Structured Prediction for Speaker Identification in TV SeriesAnnual Conference of the International Speech Communication Association, Jan 2015, Dresden, Germany. ⟨10.21437/Interspeech.2015-83⟩ |
|
|
Apprentissage par imitation pour l'étiquetage de séquences : vers une formalisation des méthodes d'étiquetage « easy-first »22ièmeTraitement Automatique des Langues Naturelles, Caen, 2015, Jan 2015, Caen, France |
|
|
Cross-Lingual Part-of-Speech Tagging through Ambiguous LearningConference on Empirical Methods in Natural Language Processing, Oct 2014, Doha, Qatar. pp.1779 - 1785 |
Apprentissage partiellement supervisé d'un étiqueteur morpho-syntaxique par transfert cross-lingueConférence sur le Traitement Automatique des Langues Naturelles, Jul 2014, Marseille, France. pp.173-183 |
|
|
|
La tâche de prédiction de la qualité. Session 5 - Mesure de la qualité en TATralogy II. Trouver le sens : où sont nos manques et nos besoins respectifs ?, Jan 2013, Paris, France. 16p |
Human Errors and Automatic Errors in Machine Translations. What are the Differences?Errare workshop : Erreurs humaines et des machines dans le traitement de données multimédias, multimodales et multilingues, Nov 2013, Ermenonville, France |
|
|
|
Design and Analysis of a Large Corpus of Post-Edited Translations: Quality Estimation, Failure Analysis and the Variability of Post-EditionMachine Translation Summit XIV, Sep 2013, Nice, France |
|
|
Un corpus d'erreurs de traduction20e conférence sur le Traitement Automatique des Langues Naturelles (TALN'2013), Jun 2013, Les Sables d'Olonne, France. pp.723-730 |
Fast large-margin learning for statistical machine translationInternational Conference on Intelligent Text Processing and Computational Linguistics, Jan 2013, Samos, Greece |
|
|
|
Résolution des coréférences dans des comptes rendus cliniques. Une expérimentation issue du défi i2b2/VA 2011RFIA 2012 (Reconnaissance des Formes et Intelligence Artificielle), Jan 2012, Lyon, France. pp.978-2-9539515-2-3 |
Non-linear n-best list reranking with few featuresConference of the Association for Machine Translation in the Americas, Jan 2012, San Diego, United States |
|
|
|
Computing lattice BLEU Oracle scores for machine translation13th Conference of the European Chapter of the Association for computational Linguistics, Association for Computational Linguistics, Apr 2012, Avignon, France. pp.120 - 129 |
|
|
LIMSI @ WMT11Sixth Workshop on Statistical Machine Translation (WMT 11), Jul 2011, Edinburgh, United Kingdom. pp.309-315 |
Ré-ordonnancement pour l'apprentissage de transformations de documents HTMLExtraction et Gestion des Connaissances (EGC), Jan 2007, Namur, Belgique. pp.727-738 |
|
From Layout to Semantic: A Reranking Model for Mapping Web Documents to Mediated XML RepresentationsRIAO International Conference on Large-Scale Semantic Access to Content, May 2007, Pittsburgh, United States. pp.433-448 |
|
Probabilistic Model for Structured Document Mapping5th International Conference on Machine Learning and Data Mining for Pattern Recognition (MLDM'07'), Jul 2007, Leizig, Germany. pp.854-867, ⟨10.1007/978-3-540-73499-4_64⟩ |
|
Modèle probabiliste pour l'extraction de structures dans les documents semi-structurés: Application aux documents Web3eme Conference en Recherche d'Information et Applications (CORIA'06), Mar 2006, Lyon, France. pp.169-180 |
|
Classification automatique de structures arborescentes à l’aide du noyau de Fisher: Application aux documents XML6ème Congrès européen de science des systèmes, Sep 2005, Paris, France |
|
Classification automatique de documents structurés. Application au corpus d’arbres étiquetés de type XMLCORIA 2005 - 2ème Conférence en Recherche d'Informations et Applications, Mar 2005, Grenoble, France. pp.167-184 |
|
Stochastic models for document restructurationECML'05 Workshop on Relationnal Machine Learning, Oct 2005, Porto, Portugal |
|
Restructuration automatique de documents dans les corpus semi structurés hétérogènesExtraction et Gestion de Connaissances (EGC'05), Jan 2005, Paris, France. pp.227-238 |
|
Document structure matching for heterogeneous corporaSIGIR 2004 workshop on XML and Information Retrieval, Jul 2004, Sheffield, United Kingdom |
|
|
The SPECTRANS System Description for the WMT22 Biomedical Task7th conference on machine translation (WMT22), EMNLP 2022, Dec 2022, Abu Dhabi, United Arab Emirates. |
|
|
Screening Gender Transfer in Neural Machine TranslationBlackBoxNLP 2021, Nov 2021, Punta Cana, Dominican Republic |
|
|
Control of chaotic systems by deep reinforcement learningDynamical Methods in Data-based Exploration of Complex Systems, international workshop, Oct 2019, Dresden, Germany |
|
|
A Corpus of Machine Translation Errors Extracted from Translation Students Exercises9th International Conference on Language Resources and Evaluation (LREC 2014), May 2014, Reykjavik, Iceland. pp.3585-3588, 2014, Proceedings of the Ninth Language Resources and Evaluation Conference (LREC 2014), 26-31 May, Reykjavik, Iceland |
|
|
Traduction et IA : comment et pourquoi les giga-modèles multilingues vont révolutionner la traduction automatique2025 |
|
|
Assessing the Impact of Anisotropy in Neural Representations of Speech: A Case Study on Keyword Spotting2025 |
|
|
Control of chaotic systems by Deep Reinforcement Learning2019 |
A multilingual corpus of tweets for domain adaptation[Research Report] LIMSI-CNRS; ELDA; Systran. 2017 |
|
PanParser: a Modular Implementation for Efficient Transition-Based Dependency Parsing[Technical Report] LIMSI-CNRS. 2016 |