Zobrazeno 1 - 10 of 21 pro vyhledávání: '"Mathieu Constant"'
1
Akademický článek
How to Dissect a Muppet: The Structure of Transformer Embedding Spaces
Autor: Timothee Mickus, Denis Paperno, Mathieu Constant
Publikováno v: Transactions of the Association for Computational Linguistics, Vol 10, Pp 981-996 (2022)
AbstractPretrained embeddings based on the Transformer architecture have taken the NLP community by storm. We show that they can mathematically be reframed as a sum of vector factors and showcase how to use this reframing to study the impact of each
Externí odkaz: https://doaj.org/article/36bffc5d4cdf4d4b8a1001baea1ea46d
Zobrazit plný text záznamu
2
Akademický článek
A French corpus annotated for multiword expressions and named entities
Autor: Marie Candito, Mathieu Constant, Carlos Ramisch, Agata Savary, Bruno Guillaume, Yannick Parmentier, Silvio Cordeiro
Publikováno v: Journal of Language Modelling, Vol 8, Iss 2, Pp 415–479-415–479 (2021)
We present the enrichment of a French treebank of various genres with a new annotation layer for multiword expressions (MWEs) and named entities (NEs).1 Our contribution with respect to previous work on NE and MWE annotation is the particular care ta
Externí odkaz: https://doaj.org/article/454468d4025e4a1d8817fd401120f23a
Zobrazit plný text záznamu
3
Akademický článek
Multiword Expression Processing: A Survey
Autor: Mathieu Constant, Gülşen Eryiğit, Johanna Monti, Lonneke van der Plas, Carlos Ramisch, Michael Rosner, Amalia Todirascu
Publikováno v: Computational Linguistics, Vol 43, Iss 4 (2017)
Multiword expressions (MWEs) are a class of linguistic forms spanning conventional word boundaries that are both idiosyncratic and pervasive across different languages. The structure of linguistic processing that depends on the clear distinction betw
Externí odkaz: https://doaj.org/article/1915b7472b9146c6b3d25f9ce3303ccc
Zobrazit plný text záznamu
4
Ressources linguistiques et identification automatique d’expressions polylexicales
Autor: Mathieu Constant
Publikováno v: Ingurune digitala, hizkuntzen estandarizazioa eta euskara = El entorno digital, la estandarización de las lenguas y el euskera ISBN: 9783968693934
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::b4c3a25f0b12375cf943a0e862e75589
https://doi.org/10.31819/9783968693934-008
Zobrazit plný text záznamu
6
Évaluation de méthodes et d’outils pour la lemmatisation automatique du français médiéval
Autor: Cristina Garcia Holgado, Alexei Lavrentiev, Mathieu Constant
Publikováno v: Actes de la 28e Conférence sur le Traitement Automatique des Langues Naturelles. Volume 1 : conférence principale
Traitement Automatique des Langues Naturelles
Traitement Automatique des Langues Naturelles, 2021, Lille, France. pp.153-161
HAL
International audience; Pour les langues historiques non stabilisées comme le français médiéval, la lemmatisation automatique présente toujours des défis, car cette langue connaît une forte variation graphique. Dans cet article, nous dressons
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::1b1ebc9bf454df3a11854f848a670923
https://hal.science/hal-03265897/file/44.pdf
Zobrazit plný text záznamu
7
Rigor Mortis: Annotating MWEs with a Gamified Platform
Autor: Karën Fort, Bruno Guillaume, Yann-Alan Pilatte, Mathieu Constant, Nicolas Lefèbvre
Publikováno v: LREC 2020-Language Resources and Evaluation Conference
LREC 2020-Language Resources and Evaluation Conference, May 2020, Marseille, France
HAL
International audience; We present here Rigor Mortis, a gamified crowdsourcing platform designed to evaluate the intuition of the speakers, then train them to annotate multi-word expressions (MWEs) in French corpora. We previously showed (Fort et al.
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::50e8b6295c013b6086fd93bd2fe3448f
https://hal.inria.fr/hal-02571466/document
Zobrazit plný text záznamu
8
Definition Modeling in French
Autor: Timothee Mickus, Mathieu Constant, Denis Paperno
Publikováno v: 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 (RÉCITAL, 22e édition). Volume 2 : Traitement Automatique des Langues Naturelles
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 2 : Traitement Automatique des Langues Naturelles
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 2 : Traitement Automatique des Langues Naturelles, 2020, Nancy, France. pp.66-80
HAL
Definition modeling is a recent task that aims at producing dictionary definitions based on wordembeddings. We observe two gaps : (i) the current state of the art has yet to tackle languages otherthan English or Chinese and (ii) the purported usabili
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::a589f725e868ae8da73a37df193935bc
https://hal.archives-ouvertes.fr/hal-02784756
Zobrazit plný text záznamu
9
A French corpus annotated for multiword expressions and named entities
Autor: Marie Candito, Mathieu Constant, Carlos Ramisch, Agata Savary, Bruno Guillaume, Yannick Parmentier, Silvio Cordeiro
Publikováno v: Journal of Language Modelling
Journal of Language Modelling, 2020, 8 (2), pp.415-479. ⟨10.15398/jlm.v8i2.265⟩
Journal of Language Modelling, Institute of Computer Science, Polish Academy of Sciences, Poland, 2020, 8 (2), pp.415-479. ⟨10.15398/jlm.v8i2.265⟩
Journal of Language Modelling, Vol 8, Iss 2, Pp 415–479-415–479 (2021)
International audience; We present the enrichment of a French treebank of various genres with a new annotation layer for multiword expressions (MWEs) and named entities (NEs).1 Our contribution with respect to previous work on NE and MWE annotation i
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::202b7e4f3ae821a4ab70f90969e7f5ff
https://hal.science/hal-03016721
Zobrazit plný text záznamu
10
Mark my Word: A Sequence-to-Sequence Approach to Definition Modeling
Autor: Timothee Mickus, Denis Paperno, Mathieu Constant
Publikováno v: HAL
Proceedings of the First NLPL Workshop on Deep Learning for Natural Language Processing
Proceedings of the First NLPL Workshop on Deep Learning for Natural Language Processing, Linköping University Electronic Press, 2019
International audience; Defining words in a textual context is a useful task both for practical purposes and for gaining insight into distributed word representations. Building on the distribu-tional hypothesis, we argue here that the most natural fo
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b108a6710c80207db3863b9a5a069a5c
https://hal.archives-ouvertes.fr/hal-02362397
Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání

Omezení vyhledávání
Plný text Recenzováno Digitální knihovna AV ČR
Zdroje