Drawing a Line between Literal and Idiomatic Meanings Based on Supervised WSD
1
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Some phrases can be interpreted either idiomatically (figuratively) or literally in context, and the precise identification of idioms is indispensable for full-fledged natural language processing (NLP). To this end, we have constructed an idiom corpus for Japanese. This paper reports on the corpus and the results of an idiom identification experiment using the corpus. The corpus targets 146 ambiguous idioms, and consists of 102,846 sentences, each of which is annotated with a literal/idiom label. For idiom identification, we targeted 90 out of the 146 idioms and adopted a word sense disambiguation (WSD) method using both common WSD features and idiom-specific features. The corpus and the experiment are the largest of their kind, as far as we know. As a result, we found that a standard supervised WSD method works well for the idiom identification and achieved an accuracy of 89.25% and 88.86% with/without idiom-specific features.
Abstract
Some phrases can be interpreted either idiomatically (figuratively) or literally in context, and the precise identification of idioms is indispensable for full-fledged natural language processing (NLP). To this end, we have constructed an idiom corpus for Japanese. This paper reports on the corpus and the results of an idiom identification experiment using the corpus. The corpus targets 146 ambiguous idioms, and consists of 102,846 sentences, each of which is annotated with a literal/idiom label. For idiom identification, we targeted 90 out of the 146 idioms and adopted a word sense disambiguation (WSD) method using both common WSD features and idiom-specific features. The corpus and the experiment are the largest of their kind, as far as we know. As a result, we found that a standard supervised WSD method works well for the idiom identification and achieved an accuracy of 89.25% and 88.86% with/without idiom-specific features.
참고문헌 (18)
- Baldwin, Timothy, "Baldwin, Timothy, Bannard, Colin, Tanaka, Takaaki, and Widdows, Dominic. 2003. An empirical model of multiword expression decomposability. In Proceedings of the ACL 2003 workshop on Multiword expressions, pp.89-96", ~ (2003)
- Birke, Julia, "clustering approach for the nearly unsupervised recognition of nonliteral language. In Proceedings of the 11th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2006), pp.329-", ~ (2006)
- Cook, Paul, "Pulling their weight: Exploiting syntactic forms for the automatic identification of idiomatic expressions in context. In Proceedings of the ACL 2007 Workshop on A Broader Perspective on Multiword", ~ (2007)
- Fazly, Afsaneh, "Automatically constructing a lexicon of verb phrase idiomatic combinations. In Proceedings of the 11th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2006), pp.337-344", ~ (2006)
- Gr?oire, Nocole, "Proceedings of the Workshop on A Broader Perspective on Multiword Expressions" (2007), Association for Computational Linguistics, Prague
- Gr?oire, Nocole, "Proceedings of the LREC Workshop Towards a Shared Task for Multiword Expressions" (2008), ACL Special Interest Group on the Lexicon(SIGLEX), Marrakech
- Hashimoto, Chikara, "Construction of Domain Dictionary for Fundamental Vocabulary", pp.137~140 (2007), In ACL ’07 Poster
- Hashimoto, Chikara, "Detecting Japanese idioms with a linguistically rich dictionary", Language Resources and Evaluation, 40(3-4), pp.243~252 (2006)
- Isahara, Hitoshi, "Development of the Japanese WordNet. In The sixth international conference on Language Resources and Evaluation (LREC2008)", ~ (2008)
- Katz, Graham, "Automatic identification of non-compositional multiword expressions using latent semantic analysis. In Proceedings of the Workshop, COLING", ACL 2006, Multiword Expressions: Identifying and Exploiting Underlying, 2006
- Kawahara, Daisuke, "Case Frame Compilation from the Web using High-Performance Computing. In Proceedings of The 5th International Conference on Language Resources and Evaluation (LREC-06), pp.1344-1347", ~ (2006)
- Lee, Yoong Keok, "An empirical evaluation of knowledge sources and learning algorithms for word sense disambiguation. In EMNLP ’02: Preceedings of the ACL-02 conference on Empirical methods in natural language processing, pp.41-48", ~ (2002)
- Magnini, Bernardo, "The Role of Domain Information in Word Sense Disambiguation", Natural Language Engineering special issue in Word Sense Disambiguation, 8(3), pp.359~373 (2002)
- Sato, Satoshi, "Compilation of a comparative list of basic Japanese idioms from five sources. In IPSJ 2007-NL-178, pp.1-6 (in Japanese)", ~ (2007)
- Shudo, Kosho, "MWEs as Non-propositional Content Indicators. In the 2nd ACL Workshop in Multiword Expressions: Integrating Processing, pp.32-39", ~ (2004)
- Tanaka, Takaaki, "Word Sense Disambiguation Incorporating Lexical and Structural Semantic Information. In Proceedings of the 2007 Joint Conference on Empirical Methods in Natural", ~ (2007)
- Tsuchiya, Masatoshi, "Development and analysis of an example database of Japanese compound functional expressions. Transactions of Information Processing Society of Japan 47(", ~ (2006)
- Vapnik,Vladimir, "The Nature of Statistical Learning Theory" (1995), Springer-Verlag, New York