James Clarke & Research

Constraint-Based Sentence Compression: An Integer Programming Approach

James Clarke and Mirella Lapata. 2006. Constraint-Based Sentence Compression: An Integer Programming Approach. In Proceedings of the COLING/ACL 2006 Main Conference Poster Session, pages 144–151. Sydney, Australia.

Download talk slides.

Abstract

The ability to compress sentences while preserving their grammaticality and most of their meaning has recently received much attention. Our work views sentence compression as an optimisation problem. We develop an integer programming formulation and infer globally optimal compressions in the face of linguistically motivated constraints.We show that such a formulation allows for relatively simple and knowledge-lean compression models that do not require parallel corpora or large scale resources. The proposed approach yields results comparable and in some cases superior to state-of-the-art.

Bibtex

@inproceedings{Clarke:Lapata:06b,
  author =       {James Clarke and Mirella Lapata},
  title =        {Constraint-based Sentence Compression: An Integer
                  Programming Approach},
  booktitle =    {Proceedings of the COLING/ACL 2006 Main Conference
                  Poster Sessions},
  pages =        {144--151},
  year =         {2006},
  address =      {Sydney, Australia},
  URL =          {http://jamesclarke.net/media/papers/clarke-lapata-acl06b.pdf},
}