Sub-sentence extraction based on combinatorial optimization

Authors:
Norihito Yasuda;Masaaki Nishino;Tsutomu Hirao;Masaaki Nagata
Affiliations:
NTT Communication Science Labs, NTT Corp., Japan;NTT Communication Science Labs, NTT Corp., Japan;NTT Communication Science Labs, NTT Corp., Japan;NTT Communication Science Labs, NTT Corp., Japan
Venue:
ECIR'13 Proceedings of the 35th European conference on Advances in Information Retrieval
Year:
2013

Citing 5
Cited 0

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
A scalable global model for summarization

ILP '09 Proceedings of the Workshop on Integer Linear Programming for Natural Langauge Processing
Sentence boundary detection and the problem with the U.S.

NAACL-Short '09 Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Companion Volume: Short Papers
A study of global inference algorithms in multi-document summarization

ECIR'07 Proceedings of the 29th European conference on IR research
A class of submodular functions for document summarization

HLT '11 Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies - Volume 1

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper describes the prospect of word extraction for text summarization based on combinatorial optimization. Instead of the commonly used sentence-based approach, word-based approaches are preferable if highly-compressed summarizations are required. However, naively applying conventional methods for word extraction yields excessively fragmented summaries. We avoid this by restricting the number of selected fragments from each sentence to at most one when formulating the maximum coverage problem. Consequently, the method only choose sub-sentences as fragments. Experiments show that our method matches the ROUGE scores of state-of-the-art systems without requiring any training or special parameters.