Opinosis: A graph-based approach to abstractive summarization of highly redundant opinions

Kavita Ganesan, Cheng Xiang Zhai, Jiawei Han

Research output: Contribution to conferencePaper

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.

Original languageEnglish (US)
Pages340-348
Number of pages9
StatePublished - Dec 1 2010
Event23rd International Conference on Computational Linguistics, Coling 2010 - Beijing, China
Duration: Aug 23 2010Aug 27 2010

Other

Other23rd International Conference on Computational Linguistics, Coling 2010
CountryChina
CityBeijing
Period8/23/108/27/10

Fingerprint

evaluation
Summary
Graph
Summarization
Evaluation

ASJC Scopus subject areas

  • Language and Linguistics
  • Computational Theory and Mathematics
  • Linguistics and Language

Cite this

Ganesan, K., Zhai, C. X., & Han, J. (2010). Opinosis: A graph-based approach to abstractive summarization of highly redundant opinions. 340-348. Paper presented at 23rd International Conference on Computational Linguistics, Coling 2010, Beijing, China.

Opinosis : A graph-based approach to abstractive summarization of highly redundant opinions. / Ganesan, Kavita; Zhai, Cheng Xiang; Han, Jiawei.

2010. 340-348 Paper presented at 23rd International Conference on Computational Linguistics, Coling 2010, Beijing, China.

Research output: Contribution to conferencePaper

Ganesan, K, Zhai, CX & Han, J 2010, 'Opinosis: A graph-based approach to abstractive summarization of highly redundant opinions', Paper presented at 23rd International Conference on Computational Linguistics, Coling 2010, Beijing, China, 8/23/10 - 8/27/10 pp. 340-348.
Ganesan K, Zhai CX, Han J. Opinosis: A graph-based approach to abstractive summarization of highly redundant opinions. 2010. Paper presented at 23rd International Conference on Computational Linguistics, Coling 2010, Beijing, China.
Ganesan, Kavita ; Zhai, Cheng Xiang ; Han, Jiawei. / Opinosis : A graph-based approach to abstractive summarization of highly redundant opinions. Paper presented at 23rd International Conference on Computational Linguistics, Coling 2010, Beijing, China.9 p.
@conference{beb601898ca94bdabdbc5d91174a4466,
title = "Opinosis: A graph-based approach to abstractive summarization of highly redundant opinions",
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.",
author = "Kavita Ganesan and Zhai, {Cheng Xiang} and Jiawei Han",
year = "2010",
month = "12",
day = "1",
language = "English (US)",
pages = "340--348",
note = "23rd International Conference on Computational Linguistics, Coling 2010 ; Conference date: 23-08-2010 Through 27-08-2010",

}

TY - CONF

T1 - Opinosis

T2 - A graph-based approach to abstractive summarization of highly redundant opinions

AU - Ganesan, Kavita

AU - Zhai, Cheng Xiang

AU - Han, Jiawei

PY - 2010/12/1

Y1 - 2010/12/1

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=80052111467&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80052111467&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:80052111467

SP - 340

EP - 348

ER -