Title :
A Model of Chinese Word Sense Disambiguation Based on Combining Rule and Statistics Method
Author :
Zhang, Yangsen ; Kang, Haiyan
Author_Institution :
Comput. Sch., Beijing Inf. Sci. & Technol. Univ., Beijing, China
Abstract :
For the existing disadvantage of Word Sense Disambiguation(WSD) research methods, we have analyzed the computability and computational complexity of knowledge Dictionaries with different structure, and chosen ¿The Grammatical knowledge-base of Contemporary Chinese¿ and ¿the Semantic Knowledge-base of Contemporary Chinese¿ which written by Institute of Computational Linguistics of Peking University, and combined the People´s Daily corpus, which has been tagged word sense on, as knowledge sources for WSD. We obtained statistical knowledge and rules knowledge, which are needed by the Chinese Word Sense Disambiguation, from the selected knowledge sources, and adopted a approach of combining rule and statistics to construct the model of Word Sense Disambiguation. It has achieved a satisfactory effect of WSD.
Keywords :
computability; computational complexity; computational linguistics; dictionaries; knowledge based systems; statistics; text analysis; Institute of Computational Linguistics; Peking University; Peoples Daily corpus; chinese word sense disambiguation model; computability; computational complexity; grammatical knowledge base of contemporary Chinese; knowledge Dictionaries; rules knowledge; statistical knowledge; Computational linguistics; Data mining; Dictionaries; Educational technology; Information science; Natural language processing; Natural languages; Speech recognition; Statistics; Tagging; Combining Rule-based and Statistics-based Approaches; Word Sense Disambiguation; corpus; word sense tagging;
Conference_Titel :
Education Technology and Computer Science (ETCS), 2010 Second International Workshop on
Conference_Location :
Wuhan
Print_ISBN :
978-1-4244-6388-6
Electronic_ISBN :
978-1-4244-6389-3
DOI :
10.1109/ETCS.2010.51
