[PDF][PDF] NTOU chinese spelling check system in CLP bake-off 2014

WC Chu, CJ Lin - Proceedings of The Third CIPS-SIGHAN Joint …, 2014 - aclanthology.org
WC Chu, CJ Lin
Proceedings of The Third CIPS-SIGHAN Joint Conference on Chinese …, 2014aclanthology.org
This paper describes details of NTOU Chinese spelling check system participating in CLP-
2014 Bakeoff. Confusion sets were expanded by using two language resources, Shuowen
and Four-Corner codes. A new method to find spelling errors in legal multi-character words
was proposed. Comparison of sentence generation probabilities is the main information for
error detection and correction. A rulebased classifier and a SVM-based classifier were
trained to identify spelling errors. Two formal runs were submitted, and the rule-based …
Abstract
This paper describes details of NTOU Chinese spelling check system participating in CLP-2014 Bakeoff. Confusion sets were expanded by using two language resources, Shuowen and Four-Corner codes. A new method to find spelling errors in legal multi-character words was proposed. Comparison of sentence generation probabilities is the main information for error detection and correction. A rulebased classifier and a SVM-based classifier were trained to identify spelling errors. Two formal runs were submitted, and the rule-based classifier achieved better performance.
aclanthology.org