Towards a unified approach for opinion question answering and summarization

Authors:
Elena Lloret;Alexandra Balahur;Manuel Palomar;Andrés Montoyo
Affiliations:
University of Alicante, Alicante, Spain;University of Alicante, Alicante, Spain;University of Alicante, Alicante, Spain;University of Alicante, Alicante, Spain
Venue:
WASSA '11 Proceedings of the 2nd Workshop on Computational Approaches to Subjectivity and Sentiment Analysis
Year:
2011

Citing 6
Cited 1

Manual and automatic evaluation of summaries

AS '02 Proceedings of the ACL-02 Workshop on Automatic Summarization - Volume 4
Towards answering opinion questions: separating facts from opinions and identifying the polarity of opinion sentences

EMNLP '03 Proceedings of the 2003 conference on Empirical methods in natural language processing
The Pyramid Method: Incorporating human content selection variation in summarization evaluation

ACM Transactions on Speech and Language Processing (TSLP)
Automatic summarising: The state of the art

Information Processing and Management: an International Journal
A Gradual Combination of Features for Building Automatic Summarisation Systems

TSD '09 Proceedings of the 12th International Conference on Text, Speech and Dialogue
Opinion Mining on Newspaper Quotations

WI-IAT '09 Proceedings of the 2009 IEEE/WIC/ACM International Joint Conference on Web Intelligence and Intelligent Agent Technology - Volume 03

Answering opinion questions on products by exploiting hierarchical organization of consumer reviews

EMNLP-CoNLL '12 Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning

Quantified Score

Hi-index	0.00

Visualization

Abstract

The aim of this paper is to present an approach to tackle the task of opinion question answering and text summarization. Following the guidelines TAC 2008 Opinion Summarization Pilot task, we propose new methods for each of the major components of the process. In particular, for the information retrieval, opinion mining and summarization stages. The performance obtained improves with respect to the state of the art by approximately 12.50%, thus concluding that the suggested approaches for these three components are adequate.