Zobrazeno 1 - 10
of 26
pro vyhledávání: '"Aurélie Herbelot"'
Autor:
Simon Preissner, Aurélie Herbelot
Publikováno v:
IJCoL, Vol 6, Iss 1, Pp 11-28 (2020)
The natural world is very diverse in terms of biological organisation, and solves problems in a wide variety of efficient and creative manners. This biodiversity is in stark contrast with the landscape of artificial models in the field of Natural Lan
Externí odkaz:
https://doaj.org/article/784415639ca749c39b6a4e3b6fc8a000
Autor:
Gemma Boleda, Aurélie Herbelot
Publikováno v:
Computational Linguistics, Vol 42, Iss 4 (2021)
Externí odkaz:
https://doaj.org/article/3878edb3d51e4b2baef6bf982fd86b01
Autor:
Alexandre Kabbach, Aurélie Herbelot
Publikováno v:
Frontiers in Artificial Intelligence, Vol 3 (2021)
In this paper we discuss the socialization hypothesis—the idea that speakers of the same (linguistic) community should share similar concepts given that they are exposed to similar environments and operate in highly-coordinated social contexts—an
Externí odkaz:
https://doaj.org/article/37f0de1aed3740a5896752c5d5d81f3e
Philosophers are often credited with particularly well-developed conceptual skills. The ‘expertise objection’ to experimental philosophy builds on this assumption to challenge inferences from findings about laypeople to conclusions about philosop
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::04cfd4f0a648286e15547ec24d3ce0f8
https://link.springer.com/article/10.1007/s11229-022-03487-3
https://link.springer.com/article/10.1007/s11229-022-03487-3
Autor:
Ann Copestake, Aurélie Herbelot
Funder: Università degli Studi di Trento
In this theoretical paper, we consider the notion of semantic competence and its relation to general language understanding—one of the most sough-after goals of Artificial Intelligence. We come back to
In this theoretical paper, we consider the notion of semantic competence and its relation to general language understanding—one of the most sough-after goals of Artificial Intelligence. We come back to
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::058f43c653380f84405177b9901248da
http://hdl.handle.net/11572/313864
http://hdl.handle.net/11572/313864
Autor:
Ludovica Pannitto, Aurélie Herbelot
Publikováno v:
CoNLL
Recurrent Neural Networks (RNNs) have been shown to capture various aspects of syntax from raw linguistic input. In most previous experiments, however, learning happens over unrealistic corpora, which do not reflect the type and amount of data a chil
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::005821a6290893f22e3029d549fbb35f
https://doi.org/10.18653/v1/2020.conll-1.13
https://doi.org/10.18653/v1/2020.conll-1.13
Autor:
Kabbach, Alexandre, Aurélie, Herbelot
Publikováno v:
GeCKo Symposium on Integrating Generic and Contextual Knowledge (2020)
Coordination is an essential aspect of linguistic communication. First, meaning itself is said to emerge from active coordination between speakers' communicative intentions and hearers' expectations (Grice, 1969). Second, speakers use coordination on
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od______1400::052e70fe62a790495242605402b71490
https://archive-ouverte.unige.ch/unige:152408
https://archive-ouverte.unige.ch/unige:152408
Autor:
Aurélie Herbelot
Publikováno v:
CoNLL
Many tasks are considered to be ‘solved’ in the computational linguistics literature, but the corresponding algorithms operate in ways which are radically different from human cognition. I illustrate this by coming back to the notion of semantic
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::753a51ccc13160d7e8809fc015d15a5a
https://doi.org/10.18653/v1/2020.conll-1.27
https://doi.org/10.18653/v1/2020.conll-1.27
Autor:
Raffaella Bernardi, Aurélie Herbelot, Mariella Dimiccoli, Sandro Pezzelle, Ionut-Teodor Sorodoc
Publikováno v:
Natural Language Engineering. 24:363-392
Major advances have recently been made in merging language and vision representations. Most tasks considered so far have confined themselves to the processing of objects and lexicalised relations amongst objects (content words). We know, however, tha
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e000983414b0ecdf1241db23411b1a1f
https://doi.org/10.1017/s1351324918000128
https://doi.org/10.1017/s1351324918000128
Publikováno v:
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics : Student Research Workshop pp. 162-168
ACL (2)
Università degli di Trento-IRIS
ACL (2)
Università degli di Trento-IRIS
In this paper, we investigate the task of learning word embeddings from very sparse data in an incremental, cognitively-plausible way. We focus on the notion of ‘informativeness’, that is, the idea that some content is more valuable to the learni
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::93aa414911f0d3e37bf38ca4038dc067
https://archive-ouverte.unige.ch/unige:152014
https://archive-ouverte.unige.ch/unige:152014