Biologically Plausible Connectionist Prediction of Natural Language Thematic Relations

Autor(es)

Garcia Rosa, Joao Luis ^[1] ; Adan-Coello, Juan Manuel ^[2]

Afiliação do(s) autor(es)

^[1] Univ Sao Paulo, Dept Comp Sci, NILC Interinst Ctr Res & Dev Computat Linguist, Sao Carlos, SP - Brazil

^[2] Pontifical Catholic Univ Campinas, Comp Engn Fac, Campinas, SP - Brazil

• Tipo de documento: Artigo Científico
• Fonte: JOURNAL OF UNIVERSAL COMPUTER SCIENCE; v. 16, n. 21, p. 3245-3277, 2010.
• Citações Web of Science: 0

Resumo

In Natural Language Processing (NLP) symbolic systems, several linguistic phenomena, for instance, the thematic role relationships between sentence constituents, such as AGENT, PATIENT, and LOCATION, can be accounted for by the employment of a rule-based grammar. Another approach to NLP concerns the use of the connectionist model, which has the benefits of learning, generalization and fault tolerance, among others. A third option merges the two previous approaches into a hybrid one: a symbolic thematic theory is used to supply the connectionist network with initial knowledge. Inspired on neuroscience, it is proposed a symbolic-connectionist hybrid system called BIO theta PRED (BIOlogically plausible thematic (theta) symbolic-connectionist PREDictor), designed to reveal the thematic grid assigned to a sentence. Its connectionist architecture comprises, as input, a featural representation of the words (based on the verb/noun WordNet classification and on the classical semantic microfeature representation), and, as output, the thematic grid assigned to the sentence. BIO theta PRED is designed to ``predict{''} thematic (semantic) roles assigned to words in a sentence context, employing biologically inspired training algorithm and architecture, and adopting a psycholinguistic view of thematic theory. (AU)

• Processo FAPESP: 08/08245-4 - Aplicação de técnicas de aprendizado de máquina e lingüística computacional para tratamento de textos
• Beneficiário: João Luís Garcia Rosa
• Modalidade de apoio: Auxílio à Pesquisa - Regular