• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.5
• /
• pp.531-540
• /
• 2010

In this paper, we present a two-phase shallow semantic parsing method based on a maximum entropy model. The first phase is to recognize semantic arguments, i.e., argument identification. The second phase is to assign appropriate semantic roles to the recognized arguments, i.e., argument classification. Here, the performance of the first phase is crucial for the success of the entire system, because the second phase is performed on the regions recognized at the identification stage. In order to improve performances of the argument identification, we incorporate syntactic knowledge into its pre-processing step. More precisely, boundaries of the immediate clause and the upper clauses of a predicate obtained from clause identification are utilized for reducing the search space. Further, the distance on parse trees from the parent node of a predicate to the parent node of a parse constituent is exploited. Experimental results show that incorporation of syntactic knowledge and the separation of argument identification from the entire procedure enhance performances of the shallow semantic parsing system.

• Korean Journal of Cognitive Science
• /
• v.23 no.2
• /
• pp.249-267
• /
• 2012

Individual differences in working memory predict qualitative differences in language processing. High span comprehenders are better able to integrate probabilistic information such as plausibility and animacy, the use of which requires the computation of real world knowledge in syntactic parsing (e.g.,[1]). However, it is unclear whether similar individual differences exist in the use of informative prosodic cues. This study examines whether working memory modulates the use of prosodic boundary information in attachment ambiguity resolution. Prosodic boundaries were manipulated in globally ambiguous relative clause sentences. The results show that high span listeners are more likely to be sensitive to the distinction between different types of prosodic boundaries than low span listeners. The findings suggest that like high-level constraints, the use of low-level prosodic information is resource demanding.