Word Sense Disambiguation and Sense-Based NV Event Frame Identifier
Jia‐Lin Tsai, Wen−Lian Hsu, Jeng-Woei Su · 2002
Word sense is ambiguous in natural language processing (NLP). This phenomenon is particularly keen in cases involving noun-verb (NV) word-pairs. In Chinese processing, there is an additional difficulty in word segmentation. This paper describes a sense-based noun-verb event frame (NVEF) identifier that can be used to disambiguate word sense in Chinese sentences effectively. A knowledge representation system (the NVEF-KR tree) for the NVEF sense-pair identifier is also proposed. We use the word sense in Hownet, which is a Chinese-English bilingual knowledge-base dictionary. Our experiment shows that the NVEF identifier is able to achieve 74.8% accuracy for the test sentences based only on NVEF sense-pair knowledge. By applying the techniques of longest syllabic NVEF-word-pair first and exclusion word checking, the sense accuracy for the same test sentences can be further improved to 93.7%. There are four major reasons for the incorrect cases: (1) lack of a bottom-up tagger, (2) lack of non-NVEF knowledge, (3) inadequate word segmentation, and (4) lack of a multi-NVEF analyzer. If these four problems can be resolved, the accuracy will be 98.9%. The result of this study indicates that NVEF sense-pair knowledge is effective for word sense disambiguation and it is likely to be important for general NLP.