서술어 Bigram을 이용한 단어 유사도 측정
Word Similarity Based on Predicate-Argument Bigrams in Morphologically Analyzed Corpora
2
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
In this paper, I suggested a statistical method to measure word similarity using predicate-argument relations in bigrams from a morphologically analyzed corpus. A word network can contribute to semantic processing in natural language processing. In recent works, word networks have been constructed by the human intuition, but it spends a lot of time and lacks consistency and relevant evaluation method. Statistical methods can relate syntactic information to the human intuition. To retrieve the syntactic information from corpus, I referred to bigram-context, containing <Noun, Predicate> pairs. While English needs accurate syntactic analyses, bigram-context in Korean corpus represents enough syntactic features, especially the predicate-argument relations, because the grammatical morphemes of Koran language show the syntactic information. I used the Dekang Lin(1998) and the Weighted Jaccard(Gasperin et al., 2001) Measure for word similarity. The synonym list extracted from corpus covered 40% (recall) of synonyms in three Korean dictionaries.
Abstract
In this paper, I suggested a statistical method to measure word similarity using predicate-argument relations in bigrams from a morphologically analyzed corpus. A word network can contribute to semantic processing in natural language processing. In recent works, word networks have been constructed by the human intuition, but it spends a lot of time and lacks consistency and relevant evaluation method. Statistical methods can relate syntactic information to the human intuition. To retrieve the syntactic information from corpus, I referred to bigram-context, containing <Noun, Predicate> pairs. While English needs accurate syntactic analyses, bigram-context in Korean corpus represents enough syntactic features, especially the predicate-argument relations, because the grammatical morphemes of Koran language show the syntactic information. I used the Dekang Lin(1998) and the Weighted Jaccard(Gasperin et al., 2001) Measure for word similarity. The synonym list extracted from corpus covered 40% (recall) of synonyms in three Korean dictionaries.
참고문헌 (22)
- 국립국어원, "한국어 어휘의망 구축의 현황과 과제", 한국어 어휘의미망 구축과 사전 편찬 학술회의 (2007)
- 신효필, "미크로코스모스 온톨로지로의 한국어 기본 동사의 사상", 언어학, (49), pp.305~324 (2007), 한국언어학회
- 윤애선, "한국어 어휘의미망 구축의 현황과 과제", 한국어 어휘의미망 구축과 사전편찬 학술회의 (2007), 국립국어원
- 이성헌, "전자사전 구축을 위한 언어기술의 한 방법", 언어학, (30), pp.185~206 (2001), 한국언어학회
- 최호섭,옥철영, "한국어 의미망 구축과 활용- 명사를 중심으로 -", 한국어학, 17, pp.6~330 (2002), 한국어학회
- Collins, A., "A spreading activation theory of semantic processing", Psychological Review, 82, pp.407~428 (1975)
- Dekang Lin, "Information Theoretic definition of similarity", Proc. 15th International. Conf. on Machine Learning (1998)
- Fellbaum,C., "WordNet:An Electronic Lexical Database" (1998), MIT Press
- Gasperin A., "Syntactic-Based Methods for Measuring Word Similarity", Proceedings of TSD 2001,?4th?International Conference on Text, Speech and Dialogue, pp.116~125 (2001), Czech Republic
- Grefenstette,G., "Evaluation techniques for automatic semantic extraction: Comparing syntactic and window-based approaches", In Proceedings of the Workshop on Acquisition of Lexical Knowledge from Text (1992)
- Lee,L., "Similarity-based approaches to natural language processing", 박사, pp.1997
- Miller,G., "WordNet: An on-line lexical database", International Journal of Lexicography, 3(4) (1990)
- Quillian,M.R., "Semantic Memory, Semantic Information Processing" (1968), MIT Press
- Rada,R., "Ranking documents with a thesaurus", JASIS, 40(5), pp.304~310 (1989)
- Rada,R., "Development and application of a metric on semantic nets", IEEE Transaction on Systems Man and Cybernetics, 19(1), pp.17~30 (1989)
- Resnik,P., "WordNet and class-based probabilities" (1998), An Electronic Lexical Database, MIT Press
- Resnik,P., "Semantic Similarity in a Taxonomy: An Information-Based Measure and its Application to Problems of Ambiguity in Natural Language", Journal of Artificial Intelligence Research, 11, pp.95~130 (1999)
- Richardson,R., "Using WordNet as a knowledge base for measuring semantic similarity between words, Working paper CA-1294, Dublin City University, School of Computer Applications, Dublin, Ireland, 젨젨쟣tp:", pub, pp.w-papers, 1994[DOI]
- Stijn van Dongen, "Graph Clustering by Flow Simulation", 박사, pp.2000
- Sussna,M., "Word sense disambiguation for free-text indexing using a massive semantic network", In Proceedings of the Second International Conference on Information and Knowledge Management (1993)
- Yarowsky,D., "Word sense disambiguation using statistical models of Roget's categories trained on large corpora", Proceedings of the 14rh International Conference on Computational linguistics, COLING '92, pp.454~460 (1992)
- Young C.Park, "Automatic Thesaurus Construction Using Bayesian Networks", Information Processing & Management, 32(5) (1996)