BROWSE
Detail
Conference Paper
3-tier Word Sense Disambiguation for Compound Noun Phrase Using Verb-Phrase Pattern and Predicative Noun
Cited - time in 
Share 
Share
- Authors
- Seong Il Yang, Sang Kyu Park, Dong Yul Ra
- Issue Date
- 2006-07
- Citation
- International Technical Conference on Circuits/Systems, Computers and Communications (ITC-CSCC) 2006, pp.1-4
- Publisher
- IEEE
- Language
- English
- Type
- Conference Paper
- Abstract
- A word sense disambiguation (WSD) is a well-known problem of natural language processing. In the machine translation system, WSD takes an essential role for the proper translation of words when the source word can be translated differently, depending on the context. Previous research on WSD was mostly focused on adjacent words as context information. Therefore, in the case of compound noun phrase, WSD mainly depended on nouns surrounding a target word. This paper presents a novel method of WSD for compound noun phrases that utilizes verb-phrase patterns as a syntactic and semantic restriction. Using a light verb construction technique with predicative nouns, a new parsing algorithm can be applied to analyze the syntactic structure of noun phrases. To disambiguate senses of a target word in a compound noun phrase, we recycle verb-phrase patterns which were already used for a clause-to-clause translation in Koreanto-English machine translation system. We classified the meaning of Korean nouns with about 400 semantic codes allowing for 9 levels in the semantic hierarchy. For an experiment, we applied our method to Korean compound noun phrases which are randomly selected from Korean newspaper corpus. And, this experiment showed that our proposed method achieves promising performance.