Zobrazeno 1 - 10
of 17
pro vyhledávání: '"Pablo Ariel Duboué"'
Publikováno v:
Information Management and Big Data ISBN: 9783319905952
SIMBig (Revised Selected Papers)
SIMBig (Revised Selected Papers)
Understanding and predicting how large scale knowledge graphs change over time has direct implications in software and hardware associated with their maintenance and storage. An important subproblem is predicting invariant nodes, that is, nodes withi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5835f8d63df2c502ac62e753b2fcdfdb
https://doi.org/10.1007/978-3-319-90596-9_4
https://doi.org/10.1007/978-3-319-90596-9_4
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783319479545
IBERAMIA
IBERAMIA
A sub-task of Natural Language Generation (NLG) is the generation of referring expressions (REG). REG algorithms aim to select attributes that unambiguously identify an entity with respect to a set of distractors. Previous work has defined a methodol
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c4a7e182480f60e53e87a9ff62982fef
https://doi.org/10.1007/978-3-319-47955-2_14
https://doi.org/10.1007/978-3-319-47955-2_14
Publikováno v:
WebNLG
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b4fb06076d1f69376d54e5fa9491eb3d
https://doi.org/10.18653/v1/w16-3504
https://doi.org/10.18653/v1/w16-3504
Publikováno v:
MICAI (Special Sessions)
A sub-task of Natural Language Generation (NLG) is the generation of referring expressions (REG). REG algorithms are expected to select attributes that unambiguously identify an entity with respect to a set of distractors. In previous work we have de
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7f891ba39835cfd97db87b125c0882eb
https://doi.org/10.1109/micai.2015.10
https://doi.org/10.1109/micai.2015.10
Publikováno v:
Advances in Artificial Intelligence ISBN: 9783319064826
Canadian Conference on AI
Canadian Conference on AI
Queries performed against the open Web during working hours reveal missing content in the internal documentation within an organization. Mining such queries is thus advantageous but it must strictly adhere to privacy policy and meet privacy expectati
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7b0ae30fd0d1739321852240b6345c8a
https://doi.org/10.1007/978-3-319-06483-3_5
https://doi.org/10.1007/978-3-319-06483-3_5
Publikováno v:
SIGIR
In some IR applications, it is desirable to adopt a high precision search strategy to return a small set of documents that are highly focused and relevant to the user's information need. With these applications in mind, we investigate semantic search
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0ff2a769a6e0d469a20a74e61ba2ff26
https://doi.org/10.1145/1148170.1148247
https://doi.org/10.1145/1148170.1148247
Autor:
Paula Estrella, Pablo Ariel Duboué
Publikováno v:
INTELIGENCIA ARTIFICIAL. 9
We describe a trained system we have built, using freely available statistical packages and present experiments specically designed to improve the performance of the system in the Spanish into English task. We performed both qualitative and quantitat
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::69dfdbc1a18776eef9c4034c5f4822af
https://doi.org/10.4114/ia.v9i26.843
https://doi.org/10.4114/ia.v9i26.843
Publikováno v:
ACL
This paper demonstrates a conceptually simple but effective method of increasing the accuracy of QA systems on factoid-style questions. We define the notion of an inverted question, and show that by requiring that the answers to the original and inve
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2e9fcb766f070eb0140b406050af10a7
https://doi.org/10.3115/1220175.1220310
https://doi.org/10.3115/1220175.1220310
Publikováno v:
HLT-NAACL
State-of-the-art Question Answering (QA) systems are very sensitive to variations in the phrasing of an information need. Finding the preferred language for such a need is a valuable task. We investigate that claim by adopting a simple MT-based parap
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::968a9dd233a13a1055eea2e2d4c5ed35
https://doi.org/10.3115/1614049.1614058
https://doi.org/10.3115/1614049.1614058