Title :
An error driven method to improve rules for the recognition of Chinese modality “LE”
Author :
Zhou, Yihui ; Zan, Hongying ; Mu, Lingling ; Yuan, Yingcheng
Author_Institution :
Coll. of Inf. & Eng., Zhengzhou Univ., Zhengzhou, China
Abstract :
We have a “Trinity” way for the recognition of Chinese modality “LE”, in which dictionary, usage rule base and usage corpora combine as the knowledge base. Handcrafted rules can hardly cover all usages in the real texts. So this paper proposes an error driven method for the automatic rules improvement. Experimental results show that, after the automatic rules improvement, the recognition precision of the modality “LE” improves by over 1.85%.
Keywords :
knowledge based systems; natural language processing; pattern recognition; Chinese modality recognition; LE modality; automatic rules improvement; dictionary; error driven method; usage corpora; usage rule base; Chinese modality; automatic rules improvement; error-driven method; functional words knowledge base;
Conference_Titel :
Natural Language Processing and Knowledge Engineering (NLP-KE), 2010 International Conference on
Conference_Location :
Beijing
Print_ISBN :
978-1-4244-6896-6
DOI :
10.1109/NLPKE.2010.5587825
