Noun Sense Identification of Korean Nominal Compounds Based on Sentential Form Recovery

ETRI Journal

关键词: machine translation system;    grammatical relation;    word sense disambiguation;    nominal compound analysis;    Sense tagging;   

Others  :  1185896
DOI  :  10.4218/etrij.10.1510.0083

【 摘 要 】

In a machine translation system, word sense disambiguation has an essential role in the proper translation of words when the target word can be translated differently depending on the context. Previous research on sense identification has mostly focused on adjacent words as context information. Therefore, in the case of nominal compounds, sense tagging of unit nouns mainly depended on other nouns surrounding the target word. In this paper, we present a practical method for the sense tagging of Korean unit nouns in a nominal compound. To overcome the weakness of traditional methods regarding the data sparseness problem, the proposed method adopts complement-predicate relation knowledge that was constructed for machine translation systems. Our method is based on a sentential form recovery technique, which recognizes grammatical relationships between unit nouns. This technique makes use of the characteristics of Korean predicative nouns. To show that our method is effective on text in general domains, the experiments were performed on a test set randomly extracted from article titles in various newspaper sections.

   

【 参考文献 】

• [1]N. Ide and J. Veronis, "Introduction to the Special Issue on Word Sense Disambiguation: The State of Art," Computational Linguistics, vol. 24, no. 1, 1998, pp. 2-40.
• [2]S.W. McRoy, "Using Multiple Knowledge Sources for Word Sense Discrimination," Computational Linguistics, vol. 18, no. 1, 1992, pp. 1-30.
• [3]M.P. Hong, C.H. Kim, and S.K. Park, "Treating Unknown Light Verb Construction in Korean-to-English Patent MT," Lecture Notes Computer Science, vol. 4139, 2006, pp. 726-737.
• [4]B. Beamer et al., "UIUC: A Knowledge-Rich Approach to Identifying Semantic Relations between Nominals," Proc. ACL SemEval Workshop, 2007, pp. 386-389.
• [5]D. Davidov and A. Rappoport, "Classification of Semantic Relationships between Nominals using Pattern Clusters," Proc. ACL, 2008, pp. 227-235.
• [6]J. Pustejovsky, P. Anick, and S. Bergler "Lexical Semantic Techniques for Corpus Analysis," Computational Linguistics, vol. 19, no. 2, 1993, pp. 331-358.
• [7]Y. Kobayasi, T. Takenobu, and T. Hozumi, "Analysis of Japanese Compound Nouns Using Collocational Information," Proc. COLING, 1994, pp. 865-869.
• [8]M. Lauer, "Corpus Statistics Meet the Noun Compound: Some Empirical Results," Proc. ACL, 1995, pp. 47-54.
• [9]J. Yoon, K. Choi, and M. Song, "A Corpus-Based Approach for Korean Nominal Compound Analysis Based on Linguistic and Statistical Information," Natural Language Engineering, vol. 7, 2001, pp. 251-270.
• [10]Y.K. Kim et al., "Word Sense Disambiguation Using Lexical and Semantic Information within Local Syntactic Relations," Proc. 30th Annual Conf. IEEE Ind. Electron. Soc., 2004, pp. 3111-3114.
• [11]D. Lin, "Using Syntactic Dependency as Local Context to Resolve Word Sense Ambiguity," Proc. ACL, 1997, pp. 64-71.
• [12]P. Chen et al., "A Fully Unsupervised Word Sense Disambiguation Method Using Dependency Knowledge," Proc. HLT, 2009, pp. 28-36.
• [13]M. Hong et al., "Customizing a Korean-English MT System for Patent Translation," Proc. 10th MT-Summit, 2005, pp. 181-187.