Relabeling Syntax Trees to Improve Syntax-Based Machine Translation Quality

Abstract

We identify problems with the Penn Treebank that render it imperfect for syntaxbased machine translation and propose methods of relabeling the syntax trees to improve translation quality. We develop a system incorporating a handful of relabeling strategies that yields a statistically significant improvement of 2.3 BLEU points over a baseline syntax-based system.

Extracted Key Phrases

11 Figures and Tables

Cite this paper

@inproceedings{Huang2006RelabelingST, title={Relabeling Syntax Trees to Improve Syntax-Based Machine Translation Quality}, author={Bryant Huang and Kevin Knight}, booktitle={HLT-NAACL}, year={2006} }