Zobrazeno 1 - 10
of 35
pro vyhledávání: '"Éric Villemonte de La Clergerie"'
Publikováno v:
IEEE BigData
In contract analysis and contract automation, a knowledge base (KB) of legal entities is fundamental for performing tasks such as contract verification, contract generation and contract analytic. However, such a KB does not always exist nor can be pr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3b02918bc003d228bb6667fcd34764c1
http://arxiv.org/abs/2012.01942
http://arxiv.org/abs/2012.01942
French Contextualized Word-Embeddings with a sip of CaBeRnet: a New French Balanced Reference Corpus
Publikováno v:
CMLC-8-8th Workshop on the Challenges in the Management of Large Corpora
CMLC-8-8th Workshop on the Challenges in the Management of Large Corpora, May 2020, Marseille, France
HAL
CMLC-8-8th Workshop on the Challenges in the Management of Large Corpora, May 2020, Marseille, France
HAL
International audience; This paper describes and compares the impact of different types and size of training corpora on language models like ELMO. By asking the fundamental question of quality versus quantity we evaluate four French corpora for train
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::2a479f03b2096f43bd8734b03ba9aef4
https://hal.inria.fr/hal-02678358/file/LREC_Fabre_Ortiz.pdf
https://hal.inria.fr/hal-02678358/file/LREC_Fabre_Ortiz.pdf
Autor:
Pierre-Emmanuel Mazaré, Samuel Humeau, Éric Villemonte de la Clergerie, Antoine Bordes, Benoît Sagot, Louis Martin
Publikováno v:
1st Workshop on Automatic Text Adaptation (ATA)
1st Workshop on Automatic Text Adaptation (ATA), Nov 2018, Tilburg, Netherlands
1st Workshop on Automatic Text Adaptation (ATA), Nov 2018, Tilburg, Netherlands
International audience; The evaluation of text simplification (TS) systems remains an open challenge. As the task has common points with machine translation (MT), TS is often evaluated using MT metrics such as BLEU. However, such metrics require high
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::dc47270f44e94550e8dcef574e57f794
http://arxiv.org/abs/1901.10746
http://arxiv.org/abs/1901.10746
Publikováno v:
SemEval@NAACL-HLT
We present the INRIA approach to the suggestion mining task at SemEval 2019. The task consists of two subtasks: suggestion mining under single-domain (Subtask A) and cross-domain (Subtask B) settings. We used the Support Vector Machines algorithm tra
Publikováno v:
Digital Humanities 2018: "Puentes/ Bridges"
Digital Humanities 2018: "Puentes/ Bridges", Jun 2018, Mexico, Mexico
HAL
Digital Humanities 2018: "Puentes/ Bridges", Jun 2018, Mexico, Mexico
HAL
International audience
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::1eed3bbb14029469e4d856e0c037ad7b
https://hal.science/hal-01850080/document
https://hal.science/hal-01850080/document
Autor:
Éric Villemonte de la Clergerie, Benjamin Muller, Amal Fethi, Djam{é} Seddah, Louis Martin, Beno{î}t Sagot, Ganesh Jawahar
Publikováno v:
CoNLL Shared Task (2)
In this paper, we present the details of the neural dependency parser and the neu-ral tagger submitted by our team 'ParisNLP' to the CoNLL 2018 Shared Task on parsing from raw text to Universal Dependencies. We augment the deep Biaffine (BiAF) parser
Publikováno v:
Conference on Computational Natural Language Learning
Conference on Computational Natural Language Learning, Aug 2017, Vancouver, Canada. pp.243-252, 2017, Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies. 〈http://universaldependencies.org/conll17/〉. 〈10.18653/v1/K17-3026〉
Conference on Computational Natural Language Learning, Aug 2017, Vancouver, Canada. pp.243-252, ⟨10.18653/v1/K17-3026⟩
CoNLL Shared Task (2)
Conference on Computational Natural Language Learning, Aug 2017, Vancouver, Canada. pp.243-252, 2017, Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies. 〈http://universaldependencies.org/conll17/〉. 〈10.18653/v1/K17-3026〉
Conference on Computational Natural Language Learning, Aug 2017, Vancouver, Canada. pp.243-252, ⟨10.18653/v1/K17-3026⟩
CoNLL Shared Task (2)
International audience; We present the ParisNLP entry at the UD CoNLL 2017 parsing shared task. In addition to the UDpipe models provided, we built our own data-driven tokenization models, sentence segmenter and lexicon-based morphological analyzers.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::dac9d19c9b5d8e5873e08c49c36c4b06
https://hal.inria.fr/hal-01584168/document
https://hal.inria.fr/hal-01584168/document
Publikováno v:
HLT-NAACL
Parsing full-fledged predicate-argument structures in a deep syntax framework requires graphs to be predicted. Using the DeepBank (Flickinger et al., 2012) and the Predicate-Argument Structure treebank (Miyao and Tsujii, 2005) as a test field, we sho
Publikováno v:
International Workshop on Semantic Evaluation
International Workshop on Semantic Evaluation, Aug 2014, Dublin, Ireland
SemEval@COLING
International Workshop on Semantic Evaluation, Aug 2014, Dublin, Ireland
SemEval@COLING
International audience; This paper describes the systems deployed by the ALPAGE team to participate to the SemEval-2014 Task on Broad-Coverage Semantic Dependency Parsing. We developed two transition-based dependency parsers with extended sets of act
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1a66b6de61af37f23214fce7374e9930
https://inria.hal.science/hal-01052485/file/semeval2014_task8_alpage.pdf
https://inria.hal.science/hal-01052485/file/semeval2014_task8_alpage.pdf
Autor:
Marie Candito, Guy Perrier, Bruno Guillaume, Corentin Ribeyre, Karën Fort, Djamé Seddah, Éric Villemonte de la Clergerie
Publikováno v:
International Conference on Language Resources and Evaluation (LREC)
International Conference on Language Resources and Evaluation (LREC), May 2014, Reykjavik, Iceland
HAL
International Conference on Language Resources and Evaluation (LREC), May 2014, Reykjavik, Iceland
HAL
International audience; We define a deep syntactic representation scheme for French, which abstracts away from surface syntactic variation and diathesis alternations, and describe the annotation of deep syntactic representations on top of the surface
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::d086603494917dd19339e8438d015dfb
https://inria.hal.science/hal-00969191v2/document
https://inria.hal.science/hal-00969191v2/document