Engenharia de features linguísticas para classificação de triplas relacionais
Abstract
In this study, linguistic features were listed for classification of triples, based on a parallel corpus in Galician, Brazilian Portuguese (PT-BR) and European Spanish (EE). In the experiments, at the syntactic level, a relevant performance of features that offer greater difficulty to extract valid triples was observed, such as the co-related null object/subject and the verb-subject inversion, as well as relational triples that form ungrammatical sub-sentences. At the morphological level, it was observed that the grammatical class of the initial word of each sub-sentence, especially when they are prepositions, were relevant for the classification of the triples. estudo, elencaram-se features morfossintáticasReferences
Barbosa, G. C. G. (2018). Utilizando Features multi-idioma para classificação de triplas relacionais em português, inglês e espanhol. Masters thesis, Universidade Federal da Bahia, Salvador.
Calvet, L. (2005). As Politicas Linguísticas. Parabola, São Paulo.
Chomsky, N. (2014). The minimalist program. MIT press, Cambridge.
Chomsky, N. and Lasnik, H. (2008). The theory of principles and parameters. In Syntax, pages 506–569. De Gruyter Mouton.
de Castilho, A. T., Kato, M. A., and do Nascimento, M., editors (1973). Gramática do Português Culto falado no Brasil: a construção da sentença. Fondo de Cultura Económica, Cidade do México.
Fader, A., Soderland, S., and Etzioni, O. (2011). Identifying relations for open information extraction. Proceedings of the Conference on Empirical Methods in Natural Language Processing, 8(4):2011. p. 1535–1545.
Fanjul, A. P. (2014). Conhecendo assimetrias: a ocorrência de pronomes pessoais. In Syntax, pages 29–50. Parabola editorial.
Gamallo, P. and Garcia, M. (2011). Multilingual open information extraction. Portuguese Conference on Artificial Intelligence., 8(4):p. 1535–1545.
Gauger, H.-M. (1989). Introductión a la lingüistica románica. Gredos, Madrid.
Calvet, L. (2005). As Politicas Linguísticas. Parabola, São Paulo.
Chomsky, N. (2014). The minimalist program. MIT press, Cambridge.
Chomsky, N. and Lasnik, H. (2008). The theory of principles and parameters. In Syntax, pages 506–569. De Gruyter Mouton.
de Castilho, A. T., Kato, M. A., and do Nascimento, M., editors (1973). Gramática do Português Culto falado no Brasil: a construção da sentença. Fondo de Cultura Económica, Cidade do México.
Fader, A., Soderland, S., and Etzioni, O. (2011). Identifying relations for open information extraction. Proceedings of the Conference on Empirical Methods in Natural Language Processing, 8(4):2011. p. 1535–1545.
Fanjul, A. P. (2014). Conhecendo assimetrias: a ocorrência de pronomes pessoais. In Syntax, pages 29–50. Parabola editorial.
Gamallo, P. and Garcia, M. (2011). Multilingual open information extraction. Portuguese Conference on Artificial Intelligence., 8(4):p. 1535–1545.
Gauger, H.-M. (1989). Introductión a la lingüistica románica. Gredos, Madrid.
Published
2021-11-29
How to Cite
LUZ, Elian Conceição; SILVA, Camilla Rastely da; CLARO, Daniela Barreiro.
Engenharia de features linguísticas para classificação de triplas relacionais. In: BRAZILIAN SYMPOSIUM IN INFORMATION AND HUMAN LANGUAGE TECHNOLOGY (STIL), 13. , 2021, Evento Online.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2021
.
p. 381-388.
DOI: https://doi.org/10.5753/stil.2021.17818.
