Learning to generate summary as structured output

Authors:
Hiroya Takamura;Manabu Okumura
Affiliations:
Tokyo Institute of Technology, Yokohama, Japan;Tokyo Institute of Technology, Yokohama, Japan
Venue:
CIKM '10 Proceedings of the 19th ACM international conference on Information and knowledge management
Year:
2010

Citing 7
Cited 0

The budgeted maximum coverage problem

Information Processing Letters
Large Margin Methods for Structured and Interdependent Output Variables

The Journal of Machine Learning Research
A formal model for information selection in multi-sentence text extraction

COLING '04 Proceedings of the 20th international conference on Computational Linguistics
Predicting diverse subsets using structural SVMs

Proceedings of the 25th international conference on Machine learning
Text summarization model based on maximum coverage problem and its variant

EACL '09 Proceedings of the 12th Conference of the European Chapter of the Association for Computational Linguistics
Cutting-plane training of structural SVMs

Machine Learning
Multi-document summarization by maximizing informative content-words

IJCAI'07 Proceedings of the 20th international joint conference on Artifical intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

We propose to use a structured output learning for summary generation based on the maximum coverage problem. Our method learns a function that outputs the benefit of each conceptual unit in the document cluster for this summarization model. In the training, we iteratively run a greedy algorithm that accepts items (sentences) with different costs (length) in order to generate a summary within the given maximum length limit. We empirically show that the structured output learning works well for this task and also examine its behavior in several dierent settings.