Zobrazeno 1 - 10
of 21
pro vyhledávání: '"Florian Boudin"'
Publikováno v:
44th European Conference on Information Retrieval
44th European Conference on Information Retrieval, Apr 2022, Stavanger, Norway. pp.582-588, ⟨10.1007/978-3-030-99739-7_73⟩
Lecture Notes in Computer Science ISBN: 9783030997380
44th European Conference on Information Retrieval, Apr 2022, Stavanger, Norway. pp.582-588, ⟨10.1007/978-3-030-99739-7_73⟩
Lecture Notes in Computer Science ISBN: 9783030997380
International audience
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b46cab181fe9478f0ab8969dfcd3c16a
https://hal.science/hal-03675070
https://hal.science/hal-03675070
Publikováno v:
Expert Systems with Applications
Expert Systems with Applications, Elsevier, 2022, 187, pp.115840. ⟨10.1016/j.eswa.2021.115840⟩
Expert Systems with Applications, Elsevier, 2022, 187, pp.115840. ⟨10.1016/j.eswa.2021.115840⟩
Formulaic expressions, such as 'in this paper we propose', are helpful for authors of scholarly papers because they convey communicative functions; in the above, it is showing the aim of this paper'. Thus, resources of formulaic expressions, such as
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bb8a04c28e9a17c72dd2df1dd6570cc4
https://hal.archives-ouvertes.fr/hal-03477787
https://hal.archives-ouvertes.fr/hal-03477787
Autor:
Ygor Gallina, Florian Boudin
Publikováno v:
NAACL-HLT
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Jun 2021, Online, France. pp.4185-4193, ⟨10.18653/v1/2021.naacl-main.330⟩
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Jun 2021, Online, France. pp.4185-4193, ⟨10.18653/v1/2021.naacl-main.330⟩
Neural keyphrase generation models have recently attracted much interest due to their ability to output absent keyphrases, that is, keyphrases that do not appear in the source text. In this paper, we discuss the usefulness of absent keyphrases from a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::abce45677a4a7062163eb840d1ad8ba1
https://doi.org/10.18653/v1/2021.naacl-main.330
https://doi.org/10.18653/v1/2021.naacl-main.330
Publikováno v:
ACM/IEEE Joint Conference on Digital Libraries (JCDL)
ACM/IEEE Joint Conference on Digital Libraries (JCDL), Aug 2020, Wuhan, China. ⟨10.1145/1122445.1122456⟩
JCDL
ACM/IEEE Joint Conference on Digital Libraries (JCDL), Aug 2020, Wuhan, China. ⟨10.1145/1122445.1122456⟩
JCDL
International audience; Keyphrase extraction models are usually evaluated under different, not directly comparable, experimental setups. As a result, it remains unclear how well proposed models actually perform, and how they compare to each other. In
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::62bba1360b908150357afa0c2b3248e7
https://hal.archives-ouvertes.fr/hal-02878953/document
https://hal.archives-ouvertes.fr/hal-02878953/document
Publikováno v:
The 58th Annual Meeting of the Association for Computational Linguistics (ACL)
The 58th Annual Meeting of the Association for Computational Linguistics (ACL), Jul 2020, Online, United States. ⟨10.18653/v1/2020.acl-main.105⟩
The 58th Annual Meeting of the Association for Computational Linguistics (ACL), Jul 2020, Online, United States. ⟨10.18653/v1/2020.acl-main.105⟩
Sequence-to-sequence models have lead to significant progress in keyphrase generation, but it remains unknown whether they are reliable enough to be beneficial for document retrieval. This study provides empirical evidence that such models can signif
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e18f65d82b4c2ef458bc3bbc2a999c3e
https://hal.archives-ouvertes.fr/hal-02556086v2/document
https://hal.archives-ouvertes.fr/hal-02556086v2/document
Publikováno v:
12th International Conference on Natural Language Generation (INLG)
12th International Conference on Natural Language Generation (INLG), Oct 2019, Tokyo, Japan. pp.130-135, ⟨10.18653/v1/W19-8617⟩
INLG
12th International Conference on Natural Language Generation (INLG), Oct 2019, Tokyo, Japan. pp.130-135, ⟨10.18653/v1/W19-8617⟩
INLG
Keyphrase generation is the task of predicting a set of lexical units that conveys the main content of a source text. Existing datasets for keyphrase generation are only readily available for the scholarly domain and include non-expert annotations. I
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b612e29b81eaa0b0058fb28bce123b1e
http://arxiv.org/abs/1911.12559
http://arxiv.org/abs/1911.12559
Autor:
Florian Boudin
Publikováno v:
NAACL-HLT (2)
Proceedings of NAACL-HLT 2018
16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL HLT)
16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL HLT), Jun 2018, Nouvelle Orléans, United States. pp.667-672
Proceedings of NAACL-HLT 2018
16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL HLT)
16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL HLT), Jun 2018, Nouvelle Orléans, United States. pp.667-672
We propose an unsupervised keyphrase extraction model that encodes topical information within a multipartite graph structure. Our model represents keyphrase candidates and topics in a single graph and exploits their mutually reinforcing relationship
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1873b3c1441f2830a13b39fe2d159951
Publikováno v:
Recherche d’Information, Document et Web Sémantique
Recherche d’Information, Document et Web Sémantique, ISTE OpenScience, 2018, 1 (1)
Recherche d’Information, Document et Web Sémantique, ISTE OpenScience, 2018, 1 (1)
Cet article decrit la campagne 2016 du defi fouille de textes (DEFT), qui pour sa douzieme edition a propose aux participants de simuler la tâche d'indexation de documents scientifiques realisee par des documentalistes, experts dans des domaines de
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f659c7fb677f4662c47baa5b8a0adc81
https://doi.org/10.21494/iste.op.2018.0209
https://doi.org/10.21494/iste.op.2018.0209
Publikováno v:
Recherche d’Information, Document et Web Sémantique
Recherche d’Information, Document et Web Sémantique, ISTE OpenScience, 2018, 1 (1)
Recherche d’Information, Document et Web Sémantique, ISTE OpenScience, 2018, 1 (1)
Cet article presente la participation de l'equipe TALN du LINA au defi fouille de textes (DEFT) 2016. Pour la tâche d'indexation de documents de domaines de specialite par l'intermediaire de leurs mots-cles, nous avons propose une methode a base de
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::da624adc77ebb6c755c254b13165e741
https://doi.org/10.21494/iste.op.2018.0210
https://doi.org/10.21494/iste.op.2018.0210
Publikováno v:
8th Workshop on Building and Using Comparable Corpora (BUCC)
8th Workshop on Building and Using Comparable Corpora (BUCC), Jul 2015, Pékin, China
BUCC@ACL/IJCNLP
8th Workshop on Building and Using Comparable Corpora (BUCC), Jul 2015, Pékin, China
BUCC@ACL/IJCNLP
International audience; This paper describes the LINA system for the BUCC 2015 shared track. Following (Enright and Kondrak, 2007), our system identify comparable documents by collecting counts of hapax words. We extend this method by filtering out d
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::cbd1a43b82c7a0aa82680d72058fb9af
https://hal.archives-ouvertes.fr/hal-01185670/file/W15-3413.pdf
https://hal.archives-ouvertes.fr/hal-01185670/file/W15-3413.pdf