Discriminative Syntactic Reranking for Statistical Machine Translation

This paper describes a method that successfully exploits simple syntactic features for n-best translation candidate reranking using perceptrons. Our approach uses discriminative language modelling to rerank the nbest translations generated by a statistical machine translation system. The performance is evaluated for Arabic-to-English translation using NIST’s MT-Eval benchmarks. Whilst parse trees do not consistently help, we show how features extracted from a simple Part-ofSpeech annotation layer outperform two competitive baselines, leading to significant BLEU improvements on three different test sets.