Zobrazeno 1 - 10
of 45
pro vyhledávání: '"Luís Marujo"'
Publikováno v:
Computational Linguistics, Vol 42, Iss 2 (2021)
Externí odkaz:
https://doaj.org/article/ffb9bfa4d6c84ce9ae8faddf96a59604
Autor:
Pradeep Karuturi, William Brendel, Leonardo Neves, Sergey Tulyakov, Luís Marujo, Lahari Poddar
Publikováno v:
NAACL-HLT (2)
Tracking user reported bugs requires considerable engineering effort in going through many repetitive reports and assigning them to the correct teams. This paper proposes a neural architecture that can jointly (1) detect if two bug reports are duplic
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7293279dea8b1b700cf55a1c7921550e
Autor:
Anatole Gershman, Ricardo Ribeiro, David Martins de Matos, Jaime G. Carbonell, João Neto, Luís Marujo
Publikováno v:
Repositório Científico de Acesso Aberto de Portugal
Repositório Científico de Acesso Aberto de Portugal (RCAAP)
instacron:RCAAP
Repositório Científico de Acesso Aberto de Portugal (RCAAP)
instacron:RCAAP
Event detection is a fundamental information extraction task, which has been explored largely in the context of question answering, topic detection and tracking, knowledge base population, news recommendation, and automatic summarization. In this art
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f35b625a5d870e7c8ec72144d1ca6d69
https://doi.org/10.1007/s10115-016-0966-4
https://doi.org/10.1007/s10115-016-0966-4
Publikováno v:
Computational Linguistics. 42:307-343
Microblogs such as Twitter, Facebook, and Sina Weibo (China's equivalent of Twitter) are a remarkable linguistic resource. In contrast to content from edited genres such as newswire, microblogs contain discussions of virtually every topic by numerous
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0dabec6f760dfc4d9408c84a1fc66605
https://doi.org/10.1162/coli_a_00249
https://doi.org/10.1162/coli_a_00249
Publikováno v:
WWW (Companion Volume)
Making friend recommendations is an important task for social networks, as having more friends typically leads to a better user experience. Most current friend recommendations systems grow the existing network at the cost of privacy. In particular, a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::eb8e9e4b04a3946031dd9792e5ec7802
https://doi.org/10.1145/3184558.3186954
https://doi.org/10.1145/3184558.3186954
Publikováno v:
EMNLP
In this paper, we target at improving the performance of multi-label emotion classification with the help of sentiment classification. Specifically, we propose a new transfer learning architecture to divide the sentence representation into two differ
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3e02cb9a23d2a23858471cc797d729b6
https://doi.org/10.18653/v1/d18-1137
https://doi.org/10.18653/v1/d18-1137
Autor:
Anatole Gershman, Jaime G. Carbonell, Wang Ling, Luís Marujo, David Martins de Matos, João Neto, Ricardo Ribeiro
Publikováno v:
Repositório Científico de Acesso Aberto de Portugal
Repositório Científico de Acesso Aberto de Portugal (RCAAP)
instacron:RCAAP
Repositório Científico de Acesso Aberto de Portugal (RCAAP)
instacron:RCAAP
We explore an event detection framework to improve multi-document summarizationWe use distributed representations of text to address different lexical realizationsSummarization is based on the hierarchical combination of single-document summariesWe p
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::751db882cfc0b3154f517b9bbc14516f
Autor:
David Martins de Matos, Anatole Gershman, João Paulo da Silva Neto, Luís Marujo, João Carvalho, Jaime G. Carbonell
Publikováno v:
Advances in Intelligent Systems and Computing ISBN: 9783319113128
IEEE Conf. on Intelligent Systems (1)
IEEE Conf. on Intelligent Systems (1)
In this paper we present a method to improve the automatic detection of events in short sentences when in the presence of a large number of event classes. Contrary to standard classification techniques such as Support Vector Machines or Random Forest
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0c99c551c954528fc0967093cd952685
https://doi.org/10.1007/978-3-319-11313-5_72
https://doi.org/10.1007/978-3-319-11313-5_72
Autor:
Marta Aparício, Paulo Figueiredo, Ricardo Ribeiro, Luís Marujo, David Martins de Matos, Francisco Raposo
Publikováno v:
Repositório Científico de Acesso Aberto de Portugal
Repositório Científico de Acesso Aberto de Portugal (RCAAP)
instacron:RCAAP
Repositório Científico de Acesso Aberto de Portugal (RCAAP)
instacron:RCAAP
We assess the performance of generic text summarization algorithms applied to films and documentaries, using the well-known behavior of summarization of news articles as reference. We use three datasets: (i) news articles, (ii) film scripts and subti
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::dcf8f8e3d52a6a4305c495d37b6a909c
Autor:
David Martins de Matos, Luís Marujo, João Paulo da Silva Neto, Alan W. Black, Jaime G. Carbonell, Chris Dyer, Isabel Trancoso, Anatole Gershman, Wang Ling
Publikováno v:
ACL (2)
CIÊNCIAVITAE
Scopus-Elsevier
CIÊNCIAVITAE
Scopus-Elsevier
In this paper, we build a corpus of tweets from Twitter annotated with keywords using crowdsourcing methods. We identify key differences between this domain and the work performed on other domains, such as news, which makes existing approaches for au
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a66fe9418028cee5acff433f251accfc
https://doi.org/10.3115/v1/p15-2105
https://doi.org/10.3115/v1/p15-2105