JUCS - Journal of Universal Computer Science 16(21): 3245-3277, doi: 10.3217/jucs-016-21-3245
Biologically Plausible Connectionist Prediction of Natural Language Thematic Relations
expand article infoJoão Luis Garcia Rosa, Juan Manuel Adan-Coello§
‡ University of Sõo Paulo at Sõo Carlos, Sõo Carlos, Brazil§ Pontifical Catholic University of Campinas, Campinas, Brazil
Open Access
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 BIOθPRED (BIOlogically plausible thematic (θ) 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. BIOθPRED 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.
thematic (semantic) role labeling, natural language processing, biologically plausible connectionist models