Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Lina M. Rojas-Barahona"'
Publikováno v:
Frontiers in Artificial Intelligence, Vol 6 (2023)
When applied to Image-to-text models, explainability methods have two challenges. First, they often provide token-by-token explanations namely, they compute a visual explanation for each token of the generated sequence. This makes explanations expens
Externí odkaz:
https://doaj.org/article/2d11fcb56ab2484abcf36052257019f9
Autor:
Frédéric Herledan, Munshi Asadullah, Emmanuel Mory, Géraldine Damnati, Olivier Le-Blouch, Martinho Dos-Santos, Lina M. Rojas Barahona, Johannes Heinecke, Jeanyves. Lancien, Pascal Bellec, Benoit Besset
Publikováno v:
SIGdial
We present a spoken conversational question answering proof of concept that is able to answer questions about general knowledge from Wikidata. The dialogue component does not only orchestrate various components but also solve coreferences and ellipsi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::eadaa7ee71da5575c55493ec7097dc85
http://arxiv.org/abs/1909.11980
http://arxiv.org/abs/1909.11980
Publikováno v:
SIGdial
We present Graph2Bots, a tool for assisting conversational agent designers. It extracts a graph representation from human-human conversations by using unsupervised learning. The generated graph contains the main stages of the dialogue and their inner
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0af0a5c1a2dbb976cbf955dc3264ccc3
https://doi.org/10.18653/v1/w19-5915
https://doi.org/10.18653/v1/w19-5915
Publikováno v:
2015 6th International Conference on Information Systems and Economic Intelligence (SIIE).
This work explores two approaches to improve the discriminative models that are commonly used nowadays for entity detection: tree-kernels and unsupervised training. Feature-rich classifiers have been widely adopted by the Natural Language processing
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::97c7c4d1a428754b09b4eecd56f51e1d
https://doi.org/10.1109/isei.2015.7358722
https://doi.org/10.1109/isei.2015.7358722
Publikováno v:
Statistical Language and Speech Processing ISBN: 9783319257884
SLSP
SLSP
This work explores weakly supervised training of discriminative linear classifiers. Such features-rich classifiers have been widely adopted by the Natural Language processing NLP community because of their powerful modeling capacity and their support
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8b9428400ac08f971ae929d061443205
https://doi.org/10.1007/978-3-319-25789-1_23
https://doi.org/10.1007/978-3-319-25789-1_23
Publikováno v:
Computational Linguistics and Intelligent Text Processing ISBN: 9783642549052
CICLing (1)
CICLing (1)
This work proposes a Bayesian approach to learn the behavior of human characters that give advice and help users to complete tasks in a situated environment. We apply Bayesian Inverse Reinforcement Learning BIRL to infer this behavior in the context
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::70a88fd83d814ef995c10d59b13b87a4
https://doi.org/10.1007/978-3-642-54906-9_41
https://doi.org/10.1007/978-3-642-54906-9_41
Autor:
Silvana, Quaglini, Toni, Giorgino, Lina M, Rojas-Barahona, Ezio, Caffi, Mauro, De Vito, Alessandra, Persico, Anna, Cavallini
Publikováno v:
Studies in health technology and informatics. 150
The system described in this paper is aimed at improving the clinical workflow of post-stroke patients under oral anticoagulant therapy (OAT). The system helps both physicians and patients during the periodic control visits necessary to assess the an
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=pmid________::45fb04461020fb4b3670ec0bc3572f08
https://pubmed.ncbi.nlm.nih.gov/19745353
https://pubmed.ncbi.nlm.nih.gov/19745353