Files in this item

FilesDescriptionFormat

application/pdf

application/pdfopinosis-presentation.ppt.pdf (6MB)
Opinosis Presentation FilePDF

application/pdf

application/pdfopinosis.pdf (644kB)
Opinosis PaperPDF

Description

Title:Opinosis: A Graph Based Approach to Abstractive Summarization of Highly Redundant Opinions
Author(s):Ganesan, Kavita; Zhai, ChengXiang; Han, Jiawei
Subject(s):Graph Summarization, Text Summarization, Opinion Summarization, Text 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.
Issue Date:2010
Publisher:Coling 2010
Citation Info:Download bibtex: http://kavita-ganesan.com/publications/export/bibtex/148
Genre:Presentation / Lecture / Speech
Article
Conference Paper / Presentation
Type:Text
Language:English
URI:http://hdl.handle.net/2142/16949
Publication Status:published or submitted for publication
Peer Reviewed:is peer reviewed
Date Available in IDEALS:2010-08-30


This item appears in the following Collection(s)

Item Statistics