Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Faille, Juliette"'
In Natural Language Generation (NLG), important information is sometimes omitted in the output text. To better understand and analyse how this type of mistake arises, we focus on RDF-to-Text generation and explore two methods of probing omissions in
Externí odkaz:
http://arxiv.org/abs/2409.16707
Autor:
Faille, Juliette, Brabant, Quentin, Lecorve, Gwenole, Rojas-Barahona, Lina M., Gardent, Claire
We explore question generation in the context of knowledge-grounded dialogs focusing on explainability and evaluation. Inspired by previous work on planning-based summarisation, we present a model which instead of directly generating a question, sequ
Externí odkaz:
http://arxiv.org/abs/2404.07836
Publikováno v:
2nd Workshop on Interactive Natural Language Technology for Explainable Artificial Intelligence
2nd Workshop on Interactive Natural Language Technology for Explainable Artificial Intelligence, Dec 2020, Dublin (online), Ireland
2nd Workshop on Interactive Natural Language Technology for Explainable Artificial Intelligence, Dec 2020, Dublin (online), Ireland
International audience; End-to-end encoder-decoder approaches to data-to-text generation are often black boxes whose predictions are difficult to explain. Breaking up the end-to-end model into submodules is a natural way to address this problem. The
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::b54cf1e617df4a575f0c383689435a44
https://hal.archives-ouvertes.fr/hal-03046206
https://hal.archives-ouvertes.fr/hal-03046206
Autor:
Faille, Juliette, Gatt, A., Gardent, Claire, Moens, Marie-Francine, Huang, Xuanjing, Specia, Lucia, Wen-tau Yih , Scott
While powerful pre-trained language models have improved the fluency of text generation models, semantic adequacy -the ability to generate text that is semantically faithful to the input- remains an unsolved issue. In this paper, we introduce a novel
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od_______101::4668ad26e95351202d2d467db4f0efc8
https://dspace.library.uu.nl/handle/1874/416479
https://dspace.library.uu.nl/handle/1874/416479
End-to-end encoder-decoder approaches to data-to-text generation are often black boxes whose predictions are difficult to explain. Breaking up the end-to-end model into sub-modules is a natural way to address this problem. The traditional pre-neural
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6088a4e40143268df6d31ad60a7c4a3b
Autor:
Karapetiantz, Pierre, Audeh, Bissan, Faille, Juliette, Louët, Agnès Lillo-Le, Bousquet, Cédric
Publikováno v:
Medinfo; 2019, p964-968, 5p
Autor:
Karapetiantz P; Sorbonne Université, Inserm, université Paris 13, Laboratoire d'informatique médicale et d'ingénierie des connaissances en e-santé, LIMICS, F-75006 Paris, France., Audeh B; Sorbonne Université, Inserm, université Paris 13, Laboratoire d'informatique médicale et d'ingénierie des connaissances en e-santé, LIMICS, F-75006 Paris, France., Faille J; Sorbonne Université, Inserm, université Paris 13, Laboratoire d'informatique médicale et d'ingénierie des connaissances en e-santé, LIMICS, F-75006 Paris, France., Lillo-Le Louët A; Centre régional de pharmacovigilance HEGP, AP-HP Paris, France., Bousquet C; Sorbonne Université, Inserm, université Paris 13, Laboratoire d'informatique médicale et d'ingénierie des connaissances en e-santé, LIMICS, F-75006 Paris, France.
Publikováno v:
Studies in health technology and informatics [Stud Health Technol Inform] 2019 Aug 21; Vol. 264, pp. 964-968.