Use of a Lexical Feature Database for Partial Parsing of Chinese

The Grammatical Knowledge base of Contemporary Chinese contains detailed feature descriptions of the morphological and syntactic behavior of a more than fifty thousand Chinese words. We have provided these features to machine learning modules controlling our partial parsers, and achieved significant improvements in performance, at a very modest cost in engineering effort, and under restrictions in the quantity of training data which make it difficult to directly use lexical identities.

• Type: Conference
• Year: 2001
• Where: NLPRS
• Authors: Elliott Franco Drábek, Qiang Zhou
• Keywords: Chinese Words, Grammatical Knowledge Base, Natural Language Processing, NLPRS 2001, Syntactic Behavior