Title :
Another View of the Features in Supervised Chinese Word Sense Disambiguation
Author_Institution :
Appl. Linguistics Res. Inst., Beijing Language & Culture Univ., Beijing, China
Abstract :
Feature is very important in either supervised or unsupervised word sense disambiguation processing. This paper investigates the relationship between the number of feature and the performance of supervised Chinese word sense disambiguation on Semeval 2007 Multilingual Chinese-English Lexical Sample task. It shows that local basic feature within window size 3 provides adequate information to do disambiguation. It also discusses the influence of data sparseness from the number of feature point of view.
Keywords :
natural language processing; multilingual Chinese-English lexical sample task; supervised Chinese word sense disambiguation; unsupervised word sense disambiguation processing; Computational linguistics; Conferences; Context; Equations; Noise; Semantics; Training; Chinese word sense disambiguation; Data sparseness; Local feature; number of feature; window size;
Conference_Titel :
Computational Intelligence and Security (CIS), 2011 Seventh International Conference on
Conference_Location :
Hainan
Print_ISBN :
978-1-4577-2008-6
DOI :
10.1109/CIS.2011.286
