Zobrazeno 1 - 9
of 9
pro vyhledávání: '"Bonaventura Coppola"'
Publikováno v:
Natural Language Engineering. 21:3-47
Entailment recognition is a primary generic task in natural language inference, whose focus is to detect whether the meaning of one expression can be inferred from the meaning of the other. Accordingly, many NLP applications would benefit from high c
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ee738a0b058b05eaf423dc288cfdfae7
https://doi.org/10.1017/s1351324913000156
https://doi.org/10.1017/s1351324913000156
Publikováno v:
Computational Linguistics and Intelligent Text Processing ISBN: 9783642003813
CICLing
CICLing
Recent work on the transfer of semantic information across languages has been recently applied to the development of resources annotated with Frame information for different non-English European languages. These works are based on the assumption that
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a7672c73cd3d565350829ed12d992f6e
http://hdl.handle.net/2108/60829
http://hdl.handle.net/2108/60829
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783642021206
ESWC
ESWC
In the past, research in ontology learning from text has mainly focused on entity recognition, taxonomy induction and relation extraction. In this work we approach a challenging research issue: detecting semantic frames from texts and using them to e
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b2f773f2de36af33ba95873f65a230ec
https://doi.org/10.1007/978-3-642-02121-3_13
https://doi.org/10.1007/978-3-642-02121-3_13
Publikováno v:
HLT-NAACL (Short Papers)
Most Spoken Dialog Systems are based on speech grammars and frame/slot semantics. The semantic descriptions of input utterances are usually defined ad-hoc with no ability to generalize beyond the target application domain or to learn from annotated c
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::536d9e9f3897519f3c73b9cf65db28d8
https://doi.org/10.3115/1620853.1620879
https://doi.org/10.3115/1620853.1620879
Publikováno v:
SLT
Current Spoken Language Understanding technology is based on a simple concept annotation of word sequences, where the interdependencies between concepts and their compositional semantics are neglected. This prevents an effective handling of language
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::15fabbb19bf6d5e5823ea0033411c964
https://doi.org/10.1109/slt.2008.4777843
https://doi.org/10.1109/slt.2008.4777843
Publikováno v:
CoNLL
Scopus-Elsevier
Scopus-Elsevier
We present a four-step hierarchical SRL strategy which generalizes the classical two-level approach (boundary detection and classification). To achieve this, we have split the classification step by grouping together roles which share linguistic prop
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::605a09cb3129e97ceb48b98e937ce4c3
https://doi.org/10.3115/1706543.1706581
https://doi.org/10.3115/1706543.1706581
Publikováno v:
Proceedings of the ACL Workshop on Feature Engineering for Machine Learning in Natural Language Processing - FeatureEng '05.
Recent natural language learning research has shown that structural kernels can be effectively used to induce accurate models of linguistic phenomena. In this paper, we show that the above properties hold on a novel task related to predicate argument
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3c821023776ced5da92bda8fe7fbd412
https://doi.org/10.3115/1610230.1610239
https://doi.org/10.3115/1610230.1610239
Autor:
John M. Prager, A. Fokoue-Nkoutche, Lei Zhang, Yue Pan, Aditya Kalyanpur, Z. M. Qiu, Chris Welty, Bonaventura Coppola, Siddharth Patwardhan, B. K. Boguraev, Adam Lally, J. W. Murdock
Publikováno v:
IBM Journal of Research and Development. 56:10:1-10:14
Although the majority of evidence analysis in DeepQA is focused on unstructured information (e.g., natural-language documents), several components in the DeepQA system use structured data (e.g., databases, knowledge bases, and ontologies) to generate
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::17c1569327ea4a1975e21db3a593e872
https://doi.org/10.1147/jrd.2012.2188737
https://doi.org/10.1147/jrd.2012.2188737
Publikováno v:
Scopus-Elsevier
Evaluation of Multilingual and Multi-modal Information Retrieval ISBN: 9783540749981
CLEF (Working Notes)
Evaluation of Multilingual and Multi-modal Information Retrieval ISBN: 9783540749981
CLEF (Working Notes)
This year, besides providing support to other groups participating in cross-language Question Answering (QA) tasks, and submitting runs both for the monolingual Italian and for the cross-language Italian/English tasks, the ITC-irst participation in t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::53f1d6e0b7441eb4d5a67b1239a182a5
http://www.scopus.com/inward/record.url?eid=2-s2.0-38049141572&partnerID=MN8TOARS
http://www.scopus.com/inward/record.url?eid=2-s2.0-38049141572&partnerID=MN8TOARS