Zobrazeno 1 - 7 of 7 pro vyhledávání: '"Franck Dary"'
1
Akademický článek
Dependency Parsing with Backtracking using Deep Reinforcement Learning
Autor: Franck Dary, Maxime Petit, Alexis Nasr
Publikováno v: Transactions of the Association for Computational Linguistics, Vol 10, Pp 888-903 (2022)
AbstractGreedy algorithms for NLP such as transition-based parsing are prone to error propagation. One way to overcome this problem is to allow the algorithm to backtrack and explore an alternative solution in cases where new evidence contradicts the
Externí odkaz: https://doaj.org/article/0fbd21142bda4a2caf28f85cde902e0d
Zobrazit plný text záznamu
2
Using ASR-Generated Text for Spoken Language Modeling
Autor: Nicolas Hervé, Valentin Pelloin, Benoit Favre, Franck Dary, Antoine Laurent, Sylvain Meignier, Laurent Besacier
Publikováno v: Proceedings of BigScience Episode #5--Workshop on Challenges & Perspectives in Creating Large Language Models
Proceedings of BigScience Episode #5--Workshop on Challenges & Perspectives in Creating Large Language Models, May 2022, virtual+Dublin, France. pp.17-25, ⟨10.18653/v1/2022.bigscience-1.2⟩
International audience; This papers aims at improving spoken language modeling (LM) using very large amount of automatically transcribed speech. We leverage the INA (French National Audiovisual Institute 1) collection and obtain 19GB of text after ap
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1af6293cdfa7c325127c8c0e96bbc6e3
https://hal.science/hal-03770460/document
Zobrazit plný text záznamu
3
The Reading Machine: a Versatile Framework for Studying Incremental Parsing Strategies
Autor: Franck Dary, Alexis Nasr
Publikováno v: The 17th International Conference on Parsing Technologies
The 17th International Conference on Parsing Technologies, Aug 2021, Bangkok (virtual), Thailand
International audience; The Reading Machine, is a parsing framework that takes as input raw text and performs six standard NLP tasks: tokenization, POS tagging, morphological analysis, lemmatization, dependency parsing and sentence segmentation. It i
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7c64727532294079342164b657fdffea
https://hal.archives-ouvertes.fr/hal-03328439/file/IWPT_2021_MACAON.pdf
Zobrazit plný text záznamu
4
On the Role of Low-Level Linguistic Tasks for Reading Time Prediction
Autor: Abdellah Fourtassi, Franck Dary, Alexis Nasr
Publikováno v: Proceedings of the Annual Meeting of the Cognitive Science Society, 43(43)
43rd Annual Meeting of the Cognitive Science Society
43rd Annual Meeting of the Cognitive Science Society, Jul 2021, Vienna, Austria. pp.452
International audience; It has been shown that complexity metrics, computed by a syntactic parser, is a predictor of human reading time, which is an approximation of human sentence comprehension difficulty. Nevertheless, parsers usually take as input
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1bdc88c6f9f591a25b30cb1cf6b5a9cc
https://hal.science/hal-03303689
Zobrazit plný text záznamu
5
TALEP at CMCL 2021 Shared Task: Non Linear Combination of Low and High-Level Features for Predicting Eye-Tracking Data
Autor: Alexis Nasr, Abdellah Fourtassi, Franck Dary
Publikováno v: CMLS
Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics
Workshop on Cognitive Modeling and Computational Linguistics
Workshop on Cognitive Modeling and Computational Linguistics, Association for Computational Linguistics, Jun 2021, Online, Mexico. pp.108-113, ⟨10.18653/v1/2021.cmcl-1.13⟩
International audience; In this paper we describe our contribution to the CMCL 2021 Shared Task, which consists in predicting 5 different eye tracking variables from English tokenized text. Our approach is based on a neural network that combines both
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c4062f870c7d6481d3bea479ca16d498
https://doi.org/10.31234/osf.io/q2cs4
Zobrazit plný text záznamu
6
Typological Features for Multilingual Delexicalised Dependency Parsing
Autor: Franck Dary, Manon Scholivet, Alexis Nasr, Carlos Ramisch, Benoit Favre
Publikováno v: NAACL-HLT (1)
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Jun 2019, Minneapolis, United States. pp.3919-3930, ⟨10.18653/v1/N19-1393⟩
International audience; The existence of universal models to describe the syntax of languages has been debated for decades. The availability of resources such as the Universal Dependencies treebanks and the World Atlas of Language Structures make it
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e9c340b3ebfe370d57b185ec042f96d3
https://doi.org/10.18653/v1/n19-1393
Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání

Omezení vyhledávání
Plný text Recenzováno Digitální knihovna AV ČR
Zdroje