James Clarke & Research

Discourse Constraints for Document Compression

James Clarke and Mirella Lapata. 2010. Discourse Constraints for Document Compression. In Computational Linguistics, vol. 36(3), pages 411–441.


Sentence compression holds promise for many applications ranging from summarisation to subtitle generation. The task is typically performed on isolated sentences without taking the surrounding context into account, even though most applications would operate over entire documents. In this paper we present a discourse informed model which is capable of producing document compressions that are coherent and informative. Our model is inspired by theories of local coherence and formulated within the framework of Integer Linear Programming. Experimental results show significant improvements over a state-of-the-art discourse agnostic approach.


  author =       {James Clarke and Mirella Lapata},
  journal =      {Computational Linguistics},
  title =        {Discourse Constraints for Document Compression}
  pages =        {411--441},
  volume =       {36(3)},
  year =         {2010},