Semantic Role Tagging for Chinese at the Lexical Level

This paper reports on a study of semantic role tagging in Chinese, in the absence of a parser. We investigated the effect of using only lexical information in statistical training; and proposed to identify the relevant headwords in a sentence as a first step to partially locate the corresponding constituents to be labelled. Experiments were done on a textbook corpus and a news corpus, representing simple data and complex data respectively. Results suggested that in Chinese, simple lexical features are useful enough when constituent boundaries are known, while parse information might be more important for complicated sentences than simple ones. Several ways to improve the headword identification results were suggested, and we also plan to explore some class-based techniques for the task, with reference to existing semantic lexicons.

• Type: Conference
• Year: 2005
• Where: IJCNLP
• Authors: Oi Yee Kwong, Benjamin K. Tsou
• Keywords: IJCNLP 2005, Natural Language Processing, Relevant Headwords, Semantic Role, Simple Lexical Features