https://scholars.lib.ntu.edu.tw/handle/123456789/413091
標題: | Detection of Chinese word usage errors for non-Native Chinese learners with bidirectional LSTM | 作者: | Shiue Y.-T. Huang H.-H. HSIN-HSI CHEN |
公開日期: | 2017 | 卷: | 2 | 起(迄)頁: | 404-410 | 來源出版物: | 55th Annual Meeting of the Association for Computational Linguistics | 摘要: | Selecting appropriate words to compose a sentence is one common problem faced by non-native Chinese learners. In this paper, we propose (bidirectional) LSTM sequence labeling models and explore various features to detect word usage errors in Chinese sentences. By combining CWINDOW word embedding features and POS information, the best bidirectional LSTM model achieves accuracy 0.5138 and MRR 0.6789 on the HSK dataset. For 80.79% of the test data, the model ranks the ground-truth within the top two at position level. ? 2017 Association for Computational Linguistics. |
描述: | 55th Annual Meeting of the Association for Computational Linguistics, ACL 2017, 30 July 2017 through 4 August 2017 |
URI: | https://scholars.lib.ntu.edu.tw/handle/123456789/413091 | ISBN: | 9781945626760 | DOI: | 10.18653/v1/P17-2064 https://www.scopus.com/inward/record.uri?eid=2-s2.0-85040548384&doi=10.18653%2fv1%2fP17-2064&partnerID=40&md5=dd208e8d1a99604fde3ba74db2736c43 |
顯示於: | 資訊工程學系 |
檔案 | 描述 | 大小 | 格式 | |
---|---|---|---|---|
P17-2064.pdf | 275.39 kB | Adobe PDF | 檢視/開啟 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。