Detection of Chinese word usage errors for non-Native Chinese learners with bidirectional LSTM
Journal
55th Annual Meeting of the Association for Computational Linguistics
Journal Volume
2
Pages
404-410
ISBN
9781945626760
Date Issued
2017
Author(s)
Abstract
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.
SDGs
Description
55th Annual Meeting of the Association for Computational Linguistics, ACL 2017, 30 July 2017 through 4 August 2017
Type
conference paper
File(s)![Thumbnail Image]()
Loading...
Name
P17-2064.pdf
Size
275.39 KB
Format
Adobe PDF
Checksum
(MD5):ef3e397d0c51f8e0a854e0b5d5e5dc28