Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Bénédicte Pierrejean"'
Autor:
Ludovic Tanguy, Bénédicte Pierrejean
Publikováno v:
Proceedings of the 13th International Conference on Computational Semantics-Short Papers
13th International Conference on Computational Semantics
13th International Conference on Computational Semantics, May 2019, Gothenburg, Sweden
IWCS (2)
13th International Conference on Computational Semantics
13th International Conference on Computational Semantics, May 2019, Gothenburg, Sweden
IWCS (2)
International audience; We know that word embeddings trained using neural-based methods (such as word2vec SGNS) are sensitive to stability problems and that across two models trained using the exact same set of parameters, the nearest neighbors of a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ce9574f9ff90c147db61dba303a87a54
https://hal.archives-ouvertes.fr/hal-02073705
https://hal.archives-ouvertes.fr/hal-02073705
Autor:
Jérôme Farinas, Lola Danet, Bénédicte Pierrejean, Patrice Péran, Xavier de Boissezon, Ludovic Tanguy, Bruno Gaume, Cécile Fabre, Lydia Mai Ho-Dac, Mélanie Jucla, Julien Pinquier, Nabil Hathout
Publikováno v:
Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics.
This paper presents the first results of a multidisciplinary project, the “Evolex” project, gathering researchers in Psycholinguistics, Neuropsychology, Computer Science, Natural Language Processing and Linguistics. The Evolex project aims at pro
Autor:
Bénédicte Pierrejean, Ludovic Tanguy
Publikováno v:
Proceedings of NAACL-HLT 2018
Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop
Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop, Jun 2018, New-Orleans, United States. pp.32-39
Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop, 2018, New-Orleans, United States. Proceedings of NAACL-HLT 2018:, pp.32-39
NAACL-HLT (Student Research Workshop)
Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop
Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop, Jun 2018, New-Orleans, United States. pp.32-39
Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop, 2018, New-Orleans, United States. Proceedings of NAACL-HLT 2018:, pp.32-39
NAACL-HLT (Student Research Workshop)
International audience; We propose a method to study the variation lying between different word embeddings models trained with different parameters. We explore the variation between models trained with only one varying parameter by observing the dist
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4cb11e10531cf55f94023298c4c5ad3b
https://hal.archives-ouvertes.fr/hal-01806468
https://hal.archives-ouvertes.fr/hal-01806468
Autor:
Bénédicte Pierrejean, Ludovic Tanguy
Publikováno v:
Proceedings of the Seventh Joint Conference on Lexical and Computational Semantics
The seventh Joint Conference on Lexical and Computational Semantics
The seventh Joint Conference on Lexical and Computational Semantics, 2018, New Orleans, United States. Proceedings of the Seventh Joint Conference on Lexical and Computational Semantics pp.154-159
The seventh Joint Conference on Lexical and Computational Semantics, Jun 2018, New Orleans, United States. pp.154-159
SEM@NAACL-HLT
The seventh Joint Conference on Lexical and Computational Semantics
The seventh Joint Conference on Lexical and Computational Semantics, 2018, New Orleans, United States. Proceedings of the Seventh Joint Conference on Lexical and Computational Semantics pp.154-159
The seventh Joint Conference on Lexical and Computational Semantics, Jun 2018, New Orleans, United States. pp.154-159
SEM@NAACL-HLT
International audience; Neural word embeddings models (such as those built with word2vec) are known to have stability problems: when retraining a model with the exact same hyperparameters, words neighborhoods may change. We propose a method to estima
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::69d6d5579d8df3bbd52997775cd7d0ff
https://hal.archives-ouvertes.fr/hal-01806467
https://hal.archives-ouvertes.fr/hal-01806467