Zobrazeno 1 - 10
of 55
pro vyhledávání: '"Descampe, Antonin"'
Autor:
Bogaert, Jeremie, de Marneffe, Marie-Catherine, Descampe, Antonin, Escouflaire, Louis, Fairon, Cedrick, Standaert, Francois-Xavier
Publikováno v:
Traitement Automatique des Langues 64, 2023, ATALA, Paris
Large language models (LLMs) perform very well in several natural language processing tasks but raise explainability challenges. In this paper, we examine the effect of random elements in the training of LLMs on the explainability of their prediction
Externí odkaz:
http://arxiv.org/abs/2410.05085
Publikováno v:
In Language and Communication November 2024 99:129-140
A large number of cameras embedded on smart-phones, drones or inside cars have a direct access to external motion sensing from gyroscopes and accelerometers. On these power-limited devices, video compression must be of low-complexity. For this reason
Externí odkaz:
http://arxiv.org/abs/2001.11829
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Goossens, Samuel, Descampe, Antonin, Orban de Xivry, Jonathan, Lee, John A., Delor, Antoine, Janssens, Guillaume, Geets, Xavier *
Publikováno v:
In Physica Medica December 2015 31(8):963-968
Autor:
Bogaert, Jérémie, Escouflaire, Louis, de Marneffe, Marie-Catherine, Descampe, Antonin, Standaert, François-Xavier, Fairon, Cédrick
We present TIPECS ("Train, Infer Predictions, Explain, Clean, Start again"), a corpus cleaning method relying on a mixed approach between machine learning and manual analysis. The aim of our dataset cleaning approach is to remove tokens or segments t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od______1493::7b094b1e478e24ae0dc51130ff5d5d92
https://hdl.handle.net/2078.1/276581
https://hdl.handle.net/2078.1/276581
In this contribution, we investigate the possible use of word embeddings models for the sociolinguistic analysis of semantic change regarding different types of biases in a longitudinal corpus of journalistic articles. Word embeddings are computed th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od______1493::b8dae349509d4a52979c40e9d89bcb58
https://hdl.handle.net/2078.1/275289
https://hdl.handle.net/2078.1/275289
In this paper, we introduce the RTBF Corpus, a large diachronic corpus of 767,204 Belgian French news articles published between 2008 and 2021 by the Belgian public service media RTBF. We present the contents and structure of the corpus, along with t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od______1493::f93a21c0afa2b81743614fbb7553de6b
https://hdl.handle.net/2078.1/276580
https://hdl.handle.net/2078.1/276580
Autor:
Bogaert, Jérémie, de Marneffe, Marie-Catherine, Descampe, Antonin, Escouflaire, Louis, Fairon, Cédrick, Standaert, François-Xavier
Publikováno v:
Traitement Automatique des Langues; 2023, Vol. 64 Issue 3, p15-40, 26p
Publikováno v:
Cahiers du Journalisme; ete-hiver2023, Vol. 2 Issue 10, pR39-R66, 28p