Zobrazeno 1 - 10
of 23
pro vyhledávání: '"Y-Lan Boureau"'
Publikováno v:
Transactions of the Association for Computational Linguistics, Vol 10, Pp 857-872 (2022)
AbstractWhile improving neural dialogue agents’ factual accuracy is the object of much research, another important aspect of communication, less studied in the setting of neural dialogue, is transparency about ignorance. In this work, we analyze to
Externí odkaz:
https://doaj.org/article/ee965f3a0a96420bbb88df7384cd5405
Autor:
Kubb, Christian, Müller, Janina, Ung, Megan, Kambadur, Melanie, Poff, Spencer, Foran, Heather, Y-Lan Boureau, Li, Margaret, Smith, Eric Michael
The purpose of the data collection is to evaluate a new intervention as part of a research study. In the current project, we will develop and test the effectiveness of a new bot-based universal prevention program aimed at improving well-being. This p
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b76b5e39186acffc28536ab9eaa58b5b
Autor:
Emily Dinan, Gavin Abercrombie, A. Bergman, Shannon Spruit, Dirk Hovy, Y-Lan Boureau, Verena Rieser
Publikováno v:
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::685cf1da6c105891562e11931cba9c04
https://doi.org/10.18653/v1/2022.acl-long.284
https://doi.org/10.18653/v1/2022.acl-long.284
Publikováno v:
ACII
Inspiration moves a person to see new possibilities and transforms the way they perceive their own potential. Inspiration has received little attention in psychology, and has not been researched before in the NLP community. To the best of our knowled
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::669f5b67e7e191d50012f826d4a329d3
http://arxiv.org/abs/2109.02734
http://arxiv.org/abs/2109.02734
Autor:
Y-Lan Boureau, Ryuichiro Higashinaka, Michimasa Inaba, Julien Perez, Chiori Hori, Yuiko Tsunomori, Takaaki Hori, Seokhwan Kim, Koichiro Yoshino, Tetsuro Takahashi
Publikováno v:
Computer Speech & Language. 55:1-25
This paper describes the experimental setups and the evaluation results of the sixth Dialog System Technology Challenges (DSTC6) aiming to develop end-to-end dialogue systems. Neural network models have become a recent focus of investigation in dialo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::cbe79c8f8db9d45002c683c98e2adb39
https://doi.org/10.1016/j.csl.2018.09.004
https://doi.org/10.1016/j.csl.2018.09.004
Publikováno v:
NAACL-HLT
Conversational agents trained on large unlabeled corpora of human interactions will learn patterns and mimic behaviors therein, which include offensive or otherwise toxic behavior. We introduce a new human-and-model-in-the-loop framework for evaluati
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::cc160e58bed8ff52ce00bd356ca2a36f
https://doi.org/10.18653/v1/2021.naacl-main.235
https://doi.org/10.18653/v1/2021.naacl-main.235
Autor:
Jing Xu, Stephen Roller, Eric Michael Smith, Jason Weston, Yinhan Liu, Emily Dinan, Y-Lan Boureau, Mary Williamson, Naman Goyal, Myle Ott, Da Ju
Publikováno v:
EACL
Building open-domain chatbots is a challenging area for machine learning research. While prior work has shown that scaling neural models in the number of parameters and the size of the data they are trained on gives improved results, we highlight oth
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6facc402fb21afc93ceda800bd7370e1
https://doi.org/10.18653/v1/2021.eacl-main.24
https://doi.org/10.18653/v1/2021.eacl-main.24
Publikováno v:
ACL
Being engaging, knowledgeable, and empathetic are all desirable general qualities in a conversational agent. Previous work has introduced tasks and datasets that aim to help agents to learn those qualities in isolation and gauge how well they can exp
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e99bfcf8d246c1c08acc0fcfd0922fc1
http://arxiv.org/abs/2004.08449
http://arxiv.org/abs/2004.08449
While improving neural dialogue agents' factual accuracy is the object of much research, another important aspect of communication, less studied in the setting of neural dialogue, is transparency about ignorance. In this work, we analyze to what exte
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9768ac677e4ee6ae4d76b6cd0617ac62
Autor:
Kyunghyun Cho, Stephen Roller, Sean Welleck, Margaret Li, Ilia Kulikov, Y-Lan Boureau, Jason Weston
Publikováno v:
ACL
Generative dialogue models currently suffer from a number of problems which standard maximum likelihood training does not address. They tend to produce generations that (i) rely too much on copying from the context, (ii) contain repetitions within ut
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f7e2bed0d5d0aea03cda3cd6c4fce45a
https://doi.org/10.18653/v1/2020.acl-main.428
https://doi.org/10.18653/v1/2020.acl-main.428