- 期刊
- OpenAccess
Word Sense Disambiguation Using Multiple Contextual Features
並列摘要
Word sense disambiguation (WSD) is a technique used to identify the correct sense of polysemous words, and it is useful for many applications, such as machine translation (MT), lexical substitution, information retrieval (IR), and biomedical applications. In this paper, we propose the use of multiple contextual features, including the predicate-argument structure and named entities, to train two commonly used classifiers, Naïve Bayes (NB) and Maximum Entropy (ME), for word sense disambiguation. Experiments are conducted to evaluate the classifiers' performance on the OntoNotes corpus and are compared with classifiers trained using a set of baseline features, such as the bag-of-words, n-grams, and part-of-speech (POS) tags. Experimental results show that incorporating both predicate-argument structure and named entities yields higher classification accuracy for both classifiers than does the use of the baseline features, resulting in accuracy as high as 81.6% and 87.4%, respectively, for NB and ME.
參考文獻
延伸閱讀
- 蕭孟勤（2007）。Word Translation Disambiguation via Dependency〔碩士論文，國立清華大學〕。華藝線上圖書館。https://www.airitilibrary.com/Article/Detail?DocID=U0016-0210200715255309
- Chang, T. Y. (2020). Probing Contextualized Word Embedding with Definition [master's thesis, National Taiwan University]. Airiti Library. https://doi.org/10.6342/NTU202000521
- 王惠（2002）。A Study on Noun Sense Disambiguation Based on Syntagmatic Features。中文計算語言學期刊，7(2)，77-88。https://doi.org/10.30019/IJCLCLP.200208.0004
- Yu, L. C., Wu, C. H., Yeh, J. F., & Hovy, E. (2008). Corpus Cleanup of Mistaken Agreement Using Word Sense Disambiguation. 中文計算語言學期刊, 13(4), 405-419. https://doi.org/10.30019/IJCLCLP.200812.0002
- Lau, C. M. (2009). Loanword truncation and optimal word length [master's thesis, The University of Hong Kong]. Airiti Library. https://www.airitilibrary.com/Article/Detail?DocID=U0029-1812201200015829