Publications

Export 55 results:
Filters: Author is Wisniewski, Guillaume  [Clear All Filters]
2022
Analyzing Gender Translation Errors to Identify Information Flows between the Encoder and Decoder of a NMT System In BlackboxNLP 2022. Abu Dhabi, United Arab Emirates, 2022.
Wisniewski, Guillaume, Lichao Zhu, Nicolas Ballier, and François Yvon. "Biais de genre dans un système de traduction automatique neuronale : une étude des mécanismes de transfert cross-langue." Traitement Automatique des Langues 63 (2022): 37-61.
Guillaume, Séverine, and Guillaume Wisniewski. Déterminer la similarité entre deux langues à l'aide des modèles pré-entraînés de la parole. Une étude pilote In Journées Jointes des Groupements de Recherche Linguistique Informatique, Formelle et de Terrain (LIFT) et Traitement Automatique des Langues (TAL), Edited by Leonor Becerra, Benoît Favre, Claire Gardent and Yannick Parmentier. Marseille, France: CNRS, 2022.
Galliot, Benjamin, Guillaume Wisniewski, Séverine Guillaume, Guillaume Jacques, and Alexis Michaud. Faciliter l'accès des praticiens du Traitement Automatique des Langues à des jeux de données de langues rares : un deuxième point d'étape In Journées Jointes des Groupements de Recherche Linguistique Informatique, Formelle et de Terrain (LIFT) et Traitement Automatique des Langues (TAL), Edited by Leonor Becerra, Benoît Favre, Claire Gardent and Yannick Parmentier. Marseille, France: CNRS, 2022.
Guillaume, Séverine, Guillaume Wisniewski, Cécile Macaire, Guillaume Jacques, Alexis Michaud, Benjamin Galliot, Maximin Coavoux, Solange Rossato, Minh-Châu Nguyễn, and Maxime Fily. Fine-tuning pre-trained models for Automatic Speech Recognition: experiments on a fieldwork corpus of Japhug (Trans-Himalayan family) In ComputEL-5 5th Workshop on Computational Methods for Endangered Languages (ComputEL-5). Proceedings of ComputEL-5: Fifth Workshop on the Use of Computational Methods in the Study of Endangered Languages. Dublin, Ireland, 2022.
Guillaume, Séverine, Guillaume Wisniewski, Cécile Macaire, Guillaume Jacques, Alexis Michaud, Benjamin Galliot, Maximin Coavoux, Solange Rossato, Minh-Châu Nguyễn, and Maxime Fily. Fine-tuning pre-trained models for Automatic Speech Recognition: experiments on a fieldwork corpus of Japhug (Trans-Himalayan family) In ComputEL-5 5th Workshop on Computational Methods for Endangered Languages (ComputEL-5). Proceedings of ComputEL-5: Fifth Workshop on the Use of Computational Methods in the Study of Endangered Languages. Dublin, Ireland, 2022.
Zhu, Lichao, Guillaume Wisniewski, Nicolas Ballier, and François Yvon. Flux d'informations dans les systèmes encodeur-décodeur. Application à l'explication des biais de genre dans les systèmes de traduction automatique. In Traitement Automatique des Langues Naturelles, Edited by Yannick Estève, Tania Jiménez, Titouan Parcollet and Marcely Zanon Boito. Avignon, France: ATALA, 2022.
Zhu, Lichao, Guillaume Wisniewski, Nicolas Ballier, and François Yvon. Flux d'informations dans les systèmes encodeur-décodeur. Application à l'explication des biais de genre dans les systèmes de traduction automatique. In Traitement Automatique des Langues Naturelles, Edited by Yannick Estève, Tania Jiménez, Titouan Parcollet and Marcely Zanon Boito. Avignon, France: ATALA, 2022.
Li, Bingzhi, Guillaume Wisniewski, and Benoît Crabbé. How Distributed are Distributed Representations? An Observation on the Locality of Syntactic Information in Verb Agreement Tasks In 60th Annual Meeting of the Association for Computational Linguistics. Dublin, France: Association for Computational Linguistics, 2022.
Li, Bingzhi, Guillaume Wisniewski, and Benoît Crabbé. How Distributed are Distributed Representations? An Observation on the Locality of Syntactic Information in Verb Agreement Tasks In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). Dublin, Ireland: Association for Computational Linguistics, 2022.PDF icon 2022.acl-short.54.pdf (379.76 KB)
Li, Bingzhi, Guillaume Wisniewski, and Benoît Crabbé. How Distributed Are Distributed Representations? An Observation on the Locality of Syntactic Information in Verb Agreement Tasks In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). Dublin, Ireland: Association for Computational Linguistics, 2022.
Li, Bingzhi, Guillaume Wisniewski, and Benoît Crabbé. How Distributed are Distributed Representations? An Observation on the Locality of Syntactic Information in Verb Agreement Tasks In 60th Annual Meeting of the Association for Computational Linguistics. Dublin, France: Association for Computational Linguistics, 2022.
de Seyssel, Maureen, Guillaume Wisniewski, Emmanuel Dupoux, and Bogdan Ludusan. "Investigating the usefulness of i-vectors for automatic language characterization." Proc. Speech Prosody 2022 (2022): 460-464.
de Seyssel, Maureen, Guillaume Wisniewski, Emmanuel Dupoux, and Bogdan Ludusan. Investigating the usefulness of i-vectors for automatic language characterization In Speech Prosody 2022 - 11th International Conference on Speech Prosody. Lisbonne, Portugal, 2022.
La robustesse de la traduction neuronale : les systèmes de traduction automatique neuronale à l' épreuve de la reproductibilité de l'expérience In Journée d'étude ''Robustesse des systemes de TAL''. Paris, France, 2022.
de Seyssel, Maureen, Guillaume Wisniewski, and Emmanuel Dupoux. Is the Language Familiarity Effect gradual ? A computational modelling approach In CogSci 2022 - 44th Annual Meeting of the Cognitive Science Society. Toronto, Canada, 2022.
Guillaume, Séverine, Guillaume Wisniewski, Cécile Macaire, Guillaume Jacques, Alexis Michaud, Benjamin Galliot, Maximin Coavoux, Solange Rossato, Minh-Châu Nguyễn, and Maxime Fily. Les modèles pré-entraînés à l'épreuve des langues rares : expériences de reconnaissance de mots sur la langue japhug (sino-tibétain) In JEP 2022 - 34e Journées d'Études sur la Parole. Actes des 34e Journées d'Études sur la Parole (JEP2022). Noirmoutier, France, 2022.
Guillaume, Séverine, Guillaume Wisniewski, Cécile Macaire, Guillaume Jacques, Alexis Michaud, Benjamin Galliot, Maximin Coavoux, Solange Rossato, Minh-Châu Nguyễn, and Maxime Fily. Les modèles pré-entraînés à l'épreuve des langues rares : expériences de reconnaissance de mots sur la langue japhug (sino-tibétain) In JEP 2022 - 34e Journées d'Études sur la Parole. Actes des 34e Journées d'Études sur la Parole (JEP2022). Noirmoutier, France, 2022.
Li, Bingzhi, Guillaume Wisniewski, and 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 In Traitement Automatique des Langues Naturelles, Edited by Yannick Estève, Tania Jiménez, Titouan Parcollet and Marcely Zanon Boito. Avignon, France: ATALA, 2022.PDF icon 2022-taln.38.pdf (298.92 KB)
Guillaume, Séverine, Guillaume Wisniewski, Benjamin Galliot, Minh-Châu Nguyễn, Maxime Fily, Guillaume Jacques, and Alexis Michaud. Plugging a neural phoneme recognizer into a simple language model: a workflow for low-resource settings In Interspeech 2022 - 23rd Annual Conference of the International Speech Communication Association. Proceedings of Interspeech 2022. Incheon, South Korea, 2022.
Guillaume, Séverine, Guillaume Wisniewski, Benjamin Galliot, Minh-Châu Nguyễn, Maxime Fily, Guillaume Jacques, and Alexis Michaud. Plugging a neural phoneme recognizer into a simple language model: a workflow for low-resource settings In Interspeech 2022 - 23rd Annual Conference of the International Speech Communication Association. Proceedings of Interspeech 2022. Incheon, South Korea, 2022.
de Seyssel, Maureen, Marvin Lavechin, Yossi Adi, Emmanuel Dupoux, and Guillaume Wisniewski. Probing phoneme, language and speaker information in unsupervised speech representations In Interspeech 2022 - 23rd INTERSPEECH Conference. Incheon, South Korea, 2022.
de Seyssel, Maureen, Marvin Lavechin, Yossi Adi, Emmanuel Dupoux, and Guillaume Wisniewski. "Probing phoneme, language and speaker information in unsupervised speech representations." arXiv preprint arXiv:2203.16193 (2022).
Ballier, Nicolas, Jean-Baptiste Yunès, Guillaume Wisniewski, Lichao Zhu, and Maria Zimina-Poirot. The SPECTRANS System Description for the WMT22 Biomedical Task., 2022.
Lavechin*, Marvin, Maureen de Seyssel, and Emmanuel Dupoux. Statistical learning bootstraps early language acquisition, Edited by Hadrien Titeux, Hervé Bredin, Guillaume Wisniewski and Alejandrina Cristia., 2022.
Toward a Test Set of Dislocations in Persian for Neural Machine Translation In The Third International Workshop on NLP Solutions for Under Resourced Languages (NSURL 2022). Trente, Italy, 2022.
2021
Apprentissage automatique pour la surveillance de marques In Conférence Nationale sur les Applications Pratiques de l'Intelligence Artificielle. Saint-Etienne, France, 2021.
Li, Bingzhi, and Guillaume Wisniewski. Are Neural Networks Extracting Linguistic Properties or Memorizing Training Data? An Observation with a Multilingual Probe for Predicting Tense In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume. Online: Association for Computational Linguistics, 2021.PDF icon 2021.eacl-main.269.pdf (220.94 KB)
Li, Bingzhi, and Guillaume Wisniewski. Are Neural Networks Extracting Linguistic Properties or Memorizing Training Data? An Observation with a Multilingual Probe for Predicting Tense In EACL 2021. Kiev (on line), Ukraine, 2021.
Li, Bingzhi, and Guillaume Wisniewski. Are Neural Networks Extracting Linguistic Properties or Memorizing Training Data? An Observation with a Multilingual Probe for Predicting Tense In EACL 2021. Kiev (on line), Ukraine, 2021.
Li, Bingzhi, Guillaume Wisniewski, and Benoît Crabbé. Are Transformers a Modern Version of ELIZA? Observations on French Object Verb Agreement In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. Online and Punta Cana, Dominican Republic: Association for Computational Linguistics, 2021.PDF icon 2021.emnlp-main.377.pdf (284.3 KB)
Li, Bingzhi, Guillaume Wisniewski, and Benoît Crabbé. Are Transformers a Modern Version of ELIZA? Observations on French Object Verb Agreement In 2021 Conference on Empirical Methods in Natural Language Processing. Punta Cana, Dominican Republic, 2021.
Li, Bingzhi, Guillaume Wisniewski, and Benoît Crabbé. Are Transformers a Modern Version of ELIZA? Observations on French Object Verb Agreement In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. Online and Punta Cana, Dominican Republic: Association for Computational Linguistics, 2021.
Li, Bingzhi, Guillaume Wisniewski, and Benoît Crabbé. Are Transformers a Modern Version of ELIZA? Observations on French Object Verb Agreement In 2021 Conference on Empirical Methods in Natural Language Processing. Punta Cana, Dominican Republic, 2021.
Wisniewski, Guillaume, Lichao Zhu, Nicolas Ballier, and François Yvon. Biais de genre dans un système de traduction automatique neuronale : une étude préliminaire In Traitement Automatique des Langues Naturelles, Edited by Pascal Denis, Natalia Grabar, Amel Fraisse, Rémi Cardon, Bernard Jacquemin, Eric Kergosien and Antonio Balvet. Lille, France: ATALA, 2021.
Galliot, Benjamin, Guillaume Wisniewski, Séverine Guillaume, Laurent Besacier, Guillaume Jacques, Alexis Michaud, Solange Rossato, Minh-Châu Nguyễn, and Maxime Fily. Deux corpus audio transcrits de langues rares (japhug et na) normalisés en vue d'expériences en traitement du signal In Journées scientifiques du Groupement de recherche ''Linguistique informatique, formelle et de terrain'' (GDR LIFT). Journées GDR LIFT 2021. Grenoble, France, 2021.
Galliot, Benjamin, Guillaume Wisniewski, Séverine Guillaume, Laurent Besacier, Guillaume Jacques, Alexis Michaud, Solange Rossato, Minh-Châu Nguyễn, and Maxime Fily. Deux corpus audio transcrits de langues rares (japhug et na) normalisés en vue d'expériences en traitement du signal In Journées scientifiques du Groupement de recherche ''Linguistique informatique, formelle et de terrain'' (GDR LIFT). Journées GDR LIFT 2021. Grenoble, France, 2021.
Núñez, José Carlos Ros, Guillaume Wisniewski, and Djamé Seddah. Noisy UGC Translation at the Character Level: Revisiting Open-Vocabulary Capabilities and Robustness of Char-Based Models In W-NUT 2021 - 7th Workshop on Noisy User-generated Text (colocated with EMNLP 2021). Proceedings of the Seventh W-NUT workshop (colocated with EMNLP 2021). Punta Cana, Dominican Republic: Inria Paris, 2021.
Núñez, José Carlos Ros, Guillaume Wisniewski, and Djamé Seddah. Noisy UGC Translation at the Character Level: Revisiting Open-Vocabulary Capabilities and Robustness of Char-Based Models In W-NUT 2021 - 7th Workshop on Noisy User-generated Text (colocated with EMNLP 2021). Proceedings of the Seventh W-NUT workshop (colocated with EMNLP 2021). Punta Cana, Dominican Republic: Inria Paris, 2021.
Wisniewski, Guillaume, Lichao Zhu, Nicolas Ballier, and François Yvon. Screening Gender Transfer in Neural Machine Translation In Fourth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP. Punta Cana, Dominica: Association for computational linguistics, 2021.
Macaire, Cécile, Guillaume Wisniewski, Séverine Guillaume, Benjamin Galliot, Guillaume Jacques, Alexis Michaud, Solange Rossato, Minh-Châu Nguyễn, and Maxime Fily. Spécialisation de modèles neuronaux pour la transcription phonémique : premiers pas vers la reconnaissance de mots pour les langues rares In Journées scientifiques du Groupement de recherche ''Linguistique informatique, formelle et de terrain'' (GDR LIFT). Journées GDR LIFT 2021. Grenoble, France, 2021.
Macaire, Cécile, Guillaume Wisniewski, Séverine Guillaume, Benjamin Galliot, Guillaume Jacques, Alexis Michaud, Solange Rossato, Minh-Châu Nguyễn, and Maxime Fily. Spécialisation de modèles neuronaux pour la transcription phonémique : premiers pas vers la reconnaissance de mots pour les langues rares In Journées scientifiques du Groupement de recherche ''Linguistique informatique, formelle et de terrain'' (GDR LIFT). Journées GDR LIFT 2021. Grenoble, France, 2021.
Ballier, Nicolas, Dahn Cho, Bilal Faye, Zong-You Ke, Hanna Martikainen, Mojca Pecman, Jean-Baptiste Yunès, Guillaume Wisniewski, Lichao Zhu, and Maria Zimina-Poirot. The SPECTRANS System Description for the WMT21 Terminology Task In EMNLP 2021 SIXTH CONFERENCE ON MACHINE TRANSLATION (WMT21). Proceedings of the Sixth Conference on Machine Translation. Punta Cana, Dominican Republic: ACL, 2021.
Ballier, Nicolas, Dahn Cho, Bilal Faye, Zong-You Ke, Hanna Martikainen, Mojca Pecman, Jean-Baptiste Yunès, Guillaume Wisniewski, Lichao Zhu, and Maria Zimina-Poirot. The SPECTRANS System Description for the WMT21 Terminology Task In EMNLP 2021 SIXTH CONFERENCE ON MACHINE TRANSLATION (WMT21). Proceedings of the Sixth Conference on Machine Translation. Punta Cana, Dominican Republic: ACL, 2021.
Rosales Núñez, José Carlos, Djamé Seddah, and Guillaume Wisniewski. Understanding the Impact of UGC Specificities on Translation Quality In W-NUT 2021 - Seventh Workshop on Noisy User-generated Text (colocated with EMNLP 2021). Proceedings of the Seventh W-NUT workshop (colocated with EMNLP 2021). Punta Cana, Dominican Republic: Inria Paris, 2021.
Adams, Oliver, Benjamin Galliot, Guillaume Wisniewski, Nicholas Lambourne, Ben Foley, Rahasya Sanders-Dwyer, Janet Wiles, Alexis Michaud, Séverine Guillaume, Laurent Besacier et al. User-friendly automatic transcription of low-resource languages: Plugging ESPnet into Elpis In ComputEL-4: Fourth Workshop on the Use of Computational Methods in the Study of Endangered Languages. Proceedings of ComputEL-4: Fourth Workshop on the Use of Computational Methods in the Study of Endangered Languages. Hawai‘i, United States, 2021.
Adams, Oliver, Benjamin Galliot, Guillaume Wisniewski, Nicholas Lambourne, Ben Foley, Rahasya Sanders-Dwyer, Janet Wiles, Alexis Michaud, Séverine Guillaume, Laurent Besacier et al. User-friendly automatic transcription of low-resource languages: Plugging ESPnet into Elpis In ComputEL-4: Fourth Workshop on the Use of Computational Methods in the Study of Endangered Languages. Proceedings of ComputEL-4: Fourth Workshop on the Use of Computational Methods in the Study of Endangered Languages. Hawai‘i, United States, 2021.
2020
Michaud, Alexis, Oliver Adams, Séverine Guillaume, and Guillaume Wisniewski. Analyse d'erreurs de transcriptions phonémiques automatiques d'une langue `` rare '' : le na (mosuo) In 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, 2, Edited by Benzitoun, Christophe, Braud, Chloé, Huber, Laurine, Langlois, David, Ouni, Slim et al. Actes de la 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 . Nancy, France: ATALA, 2020.
Michaud, Alexis, Oliver Adams, Christopher Cox, Séverine Guillaume, Guillaume Wisniewski, and Benjamin Galliot. "La transcription du linguiste au miroir de l'intelligence artificielle : réflexions à partir de la transcription phonémique automatique." Bulletin de la Société de Linguistique de Paris 115 (2020): 141-166.
Wisniewski, Guillaume, Alexis Michaud, Benjamin Galliot, Laurent Besacier, Séverine Guillaume, Katya Aplonova, and Guillaume Jacques. Ouvrir aux linguistes "de terrain" un accès à la transcription automatique In 2èmes journées scientifiques du Groupement de Recherche Linguistique Informatique Formelle et de Terrain (LIFT), Edited by Thierry Poibeau, Yannick Parmentier and Emmanuel Schang. Montrouge, France: CNRS, 2020.
Wisniewski, Guillaume, Alexis Michaud, and Séverine Guillaume. Phonemic transcription of low-resource languages: To what extent can preprocessing be automated? In 1st Joint SLTU (Spoken Language Technologies for Under-resourced languages) and CCURL (Collaboration and Computing for Under-Resourced Languages) Workshop, Edited by Dorothee Beermann, Laurent Besacier, Sakriani Sakti and Claudia Soria. Proceedings of the LREC 2020 1st Joint SLTU and CCURL Workshop (SLTU-CCURL 2020). Marseille, France: European Language Resources Association (ELRA), 2020.
Wisniewski, Guillaume, Alexis Michaud, and Séverine Guillaume. Phonemic transcription of low-resource languages: To what extent can preprocessing be automated? In Proceedings of the 1st Joint SLTU (Spoken Language Technologies for Under-resourced languages) and CCURL (Collaboration and Computing for Under-Resourced Languages) Workshop. Marseille, France, 2020.