Zobrazeno 1 - 10
of 206
pro vyhledávání: '"Grau, Brigitte"'
Publikováno v:
In: Jose J. et al. (eds) Advances in Information Retrieval. ECIR 2020. Lecture Notes in Computer Science, vol 12035. Springer, Cham
In many information extraction applications, entity linking (EL) has emerged as a crucial task that allows leveraging information about named entities from a knowledge base. In this paper, we address the task of multimodal entity linking (MEL), an em
Externí odkaz:
http://arxiv.org/abs/2104.03236
Using deep learning models on small scale datasets would result in overfitting. To overcome this problem, the process of pre-training a model and fine-tuning it to the small scale dataset has been used extensively in domains such as image processing.
Externí odkaz:
http://arxiv.org/abs/1911.00712
The study of the Tip of the Tongue phenomenon (TOT) provides valuable clues and insights concerning the organisation of the mental lexicon (meaning, number of syllables, relation with other words, etc.). This paper describes a tool based on psycho-li
Externí odkaz:
http://arxiv.org/abs/1205.6832
Autor:
Grau, Brigitte, Gleize, Martin
Publikováno v:
Langages, 2018 Dec 01(212), 105-122.
Externí odkaz:
https://www.jstor.org/stable/26780871
Publikováno v:
Advances in Information Retrieval
In many information extraction applications, entity linking (EL) has emerged as a crucial task that allows leveraging information about named entities from a knowledge base. In this paper, we address the task of multimodal entity linking (MEL), an em
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2bb0c58d9187d6fa78dd8ca323df61c4
http://europepmc.org/articles/PMC7148241
http://europepmc.org/articles/PMC7148241
Recognising if a relation holds between two entities in a text plays a vital role in information extraction. To address this problem, multiple models have been proposed based on fixed or contextualised word representations. In this paper, we propose
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::43148e5d412dd18058acdce687b3c310
https://doi.org/10.5281/zenodo.4730492
https://doi.org/10.5281/zenodo.4730492
Publikováno v:
Conférence en Recherche d'Informations et Applications-CORIA 2019
Conférence en Recherche d'Information et Applications
Conférence en Recherche d'Information et Applications, Mar 2019, Lyon, France. ⟨10.24348/coria.2019.CORIA_2019_paper_19⟩
Conférence en Recherche d'Information et Applications
Conférence en Recherche d'Information et Applications, Mar 2019, Lyon, France. ⟨10.24348/coria.2019.CORIA_2019_paper_19⟩
RÉSUMÉ. La reconnaissance qu'une relation existe entre deux entités mentionnées dans un texte joue un rôle vital en extraction d'information (EI). Pour répondre à la nécessité d'annoter ma- nuellement de nombreux exemples, des paradigmes de
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7d7e3421c7f2a1220f8373423fb0a642
https://hal.archives-ouvertes.fr/hal-02281691/document
https://hal.archives-ouvertes.fr/hal-02281691/document
Autor:
Grau, Brigitte, Gleize, Martin
Publikováno v:
Langages
Langages, Armand Colin (Larousse jusqu'en 2003), 2018, 4 (212), pp.105-122
Langages, Armand Colin (Larousse jusqu'en 2003), 2018, 4 (212), pp.105-122
La reformulation occupe une place importante dans la langue et intervient dans différents contextes de communication où les locuteurs effectuent des reformula- tions pour mieux se faire comprendre par leurs interlocuteurs. Les appli- cations automa
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::15fe46ca0493eb50445fc143c993429f
https://hal.archives-ouvertes.fr/hal-02284463
https://hal.archives-ouvertes.fr/hal-02284463
Autor:
Grau, Brigitte, Gleize, Martin
Publikováno v:
CORIA 2016-Conférence en Recherche d'Informations et Applications
Conférence en Recherche d'Information et Applications
Conférence en Recherche d'Information et Applications, Mar 2016, Toulouse, France. pp.685-700
Conférence en Recherche d'Information et Applications
Conférence en Recherche d'Information et Applications, Mar 2016, Toulouse, France. pp.685-700
In order to answer question, we propose a matching algorithm that consists in generating and learning inferences needed to rely text passages to pairs (question, candidate answer). We first retrieve relevant passages, through lexical expansion involv
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a1b78278b73d713f12261d960e056d03
https://hal.science/hal-02282822v2
https://hal.science/hal-02282822v2
Publikováno v:
Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
International Joint Conference on Natural Language Processing
International Joint Conference on Natural Language Processing, Nov 2017, Taipei, Taiwan
International Joint Conference on Natural Language Processing
International Joint Conference on Natural Language Processing, Nov 2017, Taipei, Taiwan
International audience; In this paper we present a novel approach to the automatic correction of OCR-induced orthographic errors in a given text. While current systems depend heavily on large training corpora or exter- nal information, such as domain
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::4089e4c59d7520ddf7d9c36ec50ab1ab
https://hal.archives-ouvertes.fr/hal-01831147
https://hal.archives-ouvertes.fr/hal-01831147