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

In linguistics, the semantic relations between words in a sentence are accounted for, inter alia, as the assignment of thematic roles, e.g. AGENT, INSTRUMENT, etc. As in predicate logic, simple linguistic 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 Thematic Role Processor) 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 account 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 linguistic symbolic 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.