Sentence Compression as Tree Transduction

Trevor Cohn, Mirella Lapata

Research output: Contribution to journalArticlepeer-review

Abstract / Description of output

This paper presents a tree-to-tree transduction method for sentence compression. 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.
Original languageEnglish
Pages (from-to)637-674
Number of pages38
JournalJournal of Artificial Intelligence Research
Publication statusPublished - 2009


Dive into the research topics of 'Sentence Compression as Tree Transduction'. Together they form a unique fingerprint.

Cite this