Paper: Topic-Based Bengali Opinion Summarization

ACL ID C10-2027
Title Topic-Based Bengali Opinion Summarization
Venue International Conference on Computational Linguistics
Session Poster Session
Year 2010

In this paper the development of an opi- nion summarization system that works on Bengali News corpus has been described. The system identifies the sentiment in- formation in each document, aggregates them and represents the summary infor- mation in text. The present sys-tem fol- lows a topic-sentiment model for senti- ment identification and aggregation. Top- ic-sentiment model is designed as dis- course level theme identification and the topic-sentiment aggregation is achieved by theme clustering (k-means) and Doc- ument level Theme Relational Graph re- presentation. The Document Level Theme Relational Graph is finally used for candidate summary sentence selection by standard page rank algorithms used in Information Retrieval (IR). As Bengali is a resource constrained language,...