Hybrid Thematic Role Processor: Symbolic Linguistic Relations Revised by Connectionist Learning

Abstract

In linguistics, the semantic relations between words in a se ntence are accounted for, inter alia, as the assignment of thematic roles, e .g. AGENT, INSTRUMENT, etc. As in predicate logic, simple lin guistic expressions are decomposed into one predicate (often the verb) and its arguments. The predicate assigns thematic roles to the arguments, so that each sentence has a thematic grid, a structure with all thematic roles assigned by the predicate. In order to reveal the thematic grid of a sentence, a system called HTRP (Hybrid Th ematic Role Pro cessor) is proposed, in which the connectionist architecture has, as input, a featural representation of the words of a sentence, and , as output, its thematic grid. Both a random initial weight version (RIW) and a biased initial weight version (BIW) are proposed to acco unt for systems without and with initial knowledge, respectively . In BIW, initial connection weights reflect symbolic rules for thematic roles. For both versions, after supervised training, a set of final symbolic rules is extracted, which is consistently correlated to linguisticsymbolic - knowledge. In the case of BIW, this amounts to a revision of the initial rules . In RIW, symbolic rules seem to be induced from the connectionist architecture and training.