Zobrazeno 1 - 9
of 9
pro vyhledávání: '"Diego Maupomé"'
Publikováno v:
Stats, Vol 6, Iss 3, Pp 907-919 (2023)
The rise of explainable natural language processing spurred a bulk of work on datasets augmented with human explanations, as well as technical approaches to leverage them. Notably, generative large language models offer new possibilities, as they can
Externí odkaz:
https://doaj.org/article/64da6458a24e4f858a61070950360e91
Autor:
Diego Maupomé, Marie-Jean Meurs
Publikováno v:
Information, Vol 13, Iss 6, p 290 (2022)
Composing the representation of a sentence from the tokens that it comprises is difficult, because such a representation needs to account for how the words present relate to each other. The Transformer architecture does this by iteratively changing t
Externí odkaz:
https://doaj.org/article/392c9a303e0b436393fb3c4cfb968124
Autor:
Diego Maupomé, Marie-Jean Meurs
Publikováno v:
Computational Linguistics and Intelligent Text Processing ISBN: 9783031243363
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2164f2174e838c8fa514e9ec77a9770c
https://doi.org/10.1007/978-3-031-24337-0_24
https://doi.org/10.1007/978-3-031-24337-0_24
Publikováno v:
Proceedings of the Canadian Conference on Artificial Intelligence.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::19134dca543562af9531090fa5ad3dea
https://doi.org/10.21428/594757db.36acee93
https://doi.org/10.21428/594757db.36acee93
Autor:
Diego Maupomé, Maxime D. Armstrong, Raouf Belbahar, Josselin Alezot, Rhon Balassiano, Fanny Rancourt, Marc Queudot, Sébastien Mosser, Marie-Jean Meurs
Publikováno v:
Early Detection of Mental Health Disorders by Social Media Monitoring ISBN: 9783031044304
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::44bf1cc4d3390eac771245e4674cf7c2
https://doi.org/10.1007/978-3-031-04431-1_11
https://doi.org/10.1007/978-3-031-04431-1_11
Publikováno v:
Proceedings of the Canadian Conference on Artificial Intelligence.
Deep Averaging Networks (DANs) show strong performance in several key Natural Language Processing (NLP) tasks. However, their chief drawback is not accounting for the position of tokens when encoding sequences. We study how existing position encoding
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::80b709eadac5f75bc44d52f4c53a2e22
https://doi.org/10.21428/594757db.37d7654d
https://doi.org/10.21428/594757db.37d7654d
Publikováno v:
Proceedings of the Canadian Conference on Artificial Intelligence.
This paper presents an investigation of topic modeling in embedding spaces performances in the context of depression assessment. Using the textual content of social media users from the eRisk 2018 dataset, a classification task is performed employing
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ba73dffe33f6f9610c9d425f6b81ddef
https://doi.org/10.21428/594757db.9e67a9f0
https://doi.org/10.21428/594757db.9e67a9f0
Publikováno v:
Proceedings of the Canadian Conference on Artificial Intelligence.
This work proposes an approach to predict potential answers to the Beck Depression Inventory-Second Edition (BDI-II), a 21-item self-report inventory measuring the severity of depression in adolescents and adults. Predictions are based on similarity
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::685b3332c3302b555327cb039d251177
https://doi.org/10.21428/594757db.5c753c3d
https://doi.org/10.21428/594757db.5c753c3d
Publikováno v:
Advances in Artificial Intelligence ISBN: 9783030183042
Canadian Conference on AI
Canadian Conference on AI
We take interest in the early assessment of risk for depression in social media users. We focus on the eRisk 2018 dataset, which represents users as a sequence of their written online contributions. We implement four RNN-based systems to classify the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0380742a10110aef509c73776884a4cf
https://doi.org/10.1007/978-3-030-18305-9_27
https://doi.org/10.1007/978-3-030-18305-9_27