Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Fanny Rancourt"'
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
Publikováno v:
Journal of Statistical Planning and Inference. 212:114-125
For one-parameter exponential families, we provide a unified minimax result for estimating the mean under weighted squared error losses in the presence of a lower-bound restriction. The finding recovers cases for which the result is known, as well as
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d7940e658332216fd843b0e0641ff324
https://doi.org/10.1016/j.jspi.2020.10.001
https://doi.org/10.1016/j.jspi.2020.10.001
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 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