Sentence Compression as Tree Transduction
Abstract
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.
Cite
Text
Cohn and Lapata. "Sentence Compression as Tree Transduction." Journal of Artificial Intelligence Research, 2009. doi:10.1613/JAIR.2655Markdown
[Cohn and Lapata. "Sentence Compression as Tree Transduction." Journal of Artificial Intelligence Research, 2009.](https://mlanthology.org/jair/2009/cohn2009jair-sentence/) doi:10.1613/JAIR.2655BibTeX
@article{cohn2009jair-sentence,
title = {{Sentence Compression as Tree Transduction}},
author = {Cohn, Trevor and Lapata, Mirella},
journal = {Journal of Artificial Intelligence Research},
year = {2009},
pages = {637-674},
doi = {10.1613/JAIR.2655},
volume = {34},
url = {https://mlanthology.org/jair/2009/cohn2009jair-sentence/}
}