Machine Translation

, Volume 25, Issue 4, pp 317–339

Syntactic discriminative language model rerankers for statistical machine translation

Authors

    • ISLAUniversity of Amsterdam
  • Christof Monz
    • ISLAUniversity of Amsterdam
Open AccessArticle

DOI: 10.1007/s10590-011-9108-7

Cite this article as:
Carter, S. & Monz, C. Machine Translation (2011) 25: 317. doi:10.1007/s10590-011-9108-7

Abstract

This article describes a method that successfully exploits syntactic features for n-best translation candidate reranking using perceptrons. We motivate the utility of syntax by demonstrating the superior performance of parsers over n-gram language models in differentiating between Statistical Machine Translation output and human translations. Our approach uses discriminative language modelling to rerank the n-best translations generated by a statistical machine translation system. The performance is evaluated for Arabic-to-English translation using NIST’s MT-Eval benchmarks. While deep features extracted from parse trees do not consistently help, we show how features extracted from a shallow Part-of-Speech annotation layer outperform a competitive baseline and a state-of-the-art comparative reranking approach, leading to significant BLEU improvements on three different test sets.

Keywords

Statistical machine translationDiscriminative language modelsSyntax
Download to read the full article text

Copyright information

© The Author(s) 2011