University of Illinois Urbana-Champaign

Opinosis: A Graph Based Approach to Abstractive Summarization of Highly Redundant Opinions

Ganesan, Kavita; Zhai, ChengXiang; Han, Jiawei

Permalink

https://hdl.handle.net/2142/16555

Description

Title
Opinosis: A Graph Based Approach to Abstractive Summarization of Highly Redundant Opinions
Author(s)
  • Ganesan, Kavita
  • Zhai, ChengXiang
  • Han, Jiawei
Issue Date
2010
Keyword(s)
  • abstractive summarization
  • opinion summarization
  • text summarization
  • graph mining
  • graph summarization
Abstract
We present a novel graph-based summarization framework (Opinosis) that generates concise abstractive summaries of highly redundant opinions. Evaluation results on summarizing user reviews show that Opinosis summaries have better agreement with human summaries compared to the baseline extractive method. The summaries are readable, reasonably well-formed and are informative enough to convey the major opinions.
Publisher
COLING 2010
Type of Resource
text
Language
en
Permalink
http://hdl.handle.net/2142/16555

Owning Collections

Conference Proceedings and Workshop Materials - Computer Science PRIMARY