HTRP II: learning thematic relations from semantically sound sentences

HTRP-Hybrid Thematic Role Processor-is a symbolic-connectionist hybrid system that processes the thematic roles, the semantic relations between words in a sentence. However, HTRP has some limitations: the sentences must be broken into verb-noun pairs to be presented to the network. This makes it impossible for the system to deal with instances in which constraints are operative not only between the verb and one of its arguments (nouns), but also between two arguments of the same verb. Another possible drawback is training with negative examples (semantically unsound sentences). Although many researchers point out that negative inputs are necessary for a system to learn a grammar, several authors believe that, under certain circumstances, a network is able to learn in absence of negative examples. From a psycholinguistic standpoint, especially regarding language acquisition, explicit negative evidence is hardly to be expected as part of the cognitive environment. In this paper, new versions of HTRP are proposed (HTRP II) to account for the whole sentence as input with no negative examples provided during training.