A query-specific opinion summarization system
Feng Jin, Minlie Huang, Xiaoyan Zhu · 2009
This paper introduces a query-specific opinion summarization system: QOS. When input an opinion question, the system returns a summary with relevance to the opinions and target described by the question. The system has several modules to be able to do this: a question analysis and query reformulation module, a latent semantic indexing based sentence scoring module, a sentence polarity detection module, and a redundancy removal module. When tested on the standard dataset provided by NIST, the results ranked in the median and our system show some competence in this new field.