Hyun Jae Park, Yo Seop Woo

The Transactions of the Korea Information Processing Society (1994 ~ 2000), Vol. 7, No. 9, pp. 2876-2884, Sep. 2000
10.3745/KIPSTE.2000.7.9.2876,   PDF Download:

Abstract

Clausal segmentation is the method that parses Korean sentences by segmenting one long sentence into several phrases according to the predicates. So far most of researches could be useful for literary sentences, but long sentences increase complexities of the syntax analysis. Thus this paper proposed Two-Level Clausal Segmentation using sense information which was designed and implemented to solve this problem. Analysis of clausal segmentation and understanding of word senses can reduce syntactic and semantic ambiguity. Clausal segmentation using Sense Information is necessary because there are structural ambiguity of sentences and a frequent abbreviation of auxiliary word in common sentences. Two-Level Clausal Segmentation System(TLCSS) consists of Complement Selection Process(CSP) and Noncomplement Expansion Process(NEP). CSP matches sentence elements to subcategorization dictionary and noun thesaurus. As a result of this step, we can find the complement and subcategorization pattern. Secondly, NEP is the method that uses syntactic property and the others methods for noncomplement increase of growth. As a result of this step, we acquire segmented sentences. We present a technique to estimate the precision of Two-Level Clausal Segmentation System, and shows a result of Clausal Segmentation with 25,000 manually sense tagged corpus constructed by ETRI-KONAN group. An Two-Level Clausal Segmentation System shows clausal segmentation precision of 91.8%.

Statistics
Cite this article