Tevor Cohn and Mirella Lapata. 2007. Large Margin Synchronous Generation and its Application to Sentence Compression. In Proceedings of the Conference on Empirical Methods in Natural Language Processing and on Computational Natural Language Learning, 73-82. Prague.

This paper presents a tree-to-tree transduction method for text rewriting. Our model is based on synchronous tree substitution grammar, a formalism that allows local distortion of the tree topology and can thus naturally capture structural mismatches. We describe an algorithm for decoding in this framework and show how the model can be trained discriminatively within a large margin framework. Experimental results on sentence compression bring significant improvements over a state-of-the-art model.

@InProceedings{Cohn:Lapata:07b
  author = 	 {Trevor Cohn and Mirella Lapata},
  title = 	 {Large Margin Synchronous Generation and its Application
                  to Sentence Compression},
  crossref =	 {EMNLP:CONLL:07}, 
  pages =        {73--82}
}

@Proceedings{EMNLP:CONLL:07,
  title = 	 {Proceedings  of the Conference on Empirical Methods
                  in Natural Language Processing and on Computational
                  Natural Language  Learning}, 
  booktitle =    {Proceedings  of the Conference on Empirical Methods
                  in Natural Language Processing and on Computational
                  Natural Language  Learning}, 
  year = 	 2007,
  address =	 {Prague}
}