Paper: Opinion Target Extraction in Chinese News Comments

ACL ID C10-2090
Title Opinion Target Extraction in Chinese News Comments
Venue International Conference on Computational Linguistics
Session Poster Session
Year 2010

News Comments on the web express readers’ attitudes or opinions about an event or object in the corresponding news article. And opinion target extrac- tion from news comments is very impor- tant for many useful Web applications. However, many sentences in the com- ments are irregular and informal, and sometimes the opinion targets are impli- cit. Thus the task is very challenging and it has not been investigated yet. In this paper, we propose a new approach to un- iformly extracting explicit and implicit opinion targets from news comments by using Centering Theory. The approach uses global information in news articles as well as contextual information in ad- jacent sentences of comments. Our expe- rimental results verify the effectiveness of the proposed approach.