Center for Human Modeling and Simulation

An End-to-End Discriminative Approach to Machine Translation

Ben Taskar, University of Pennsylvania
Dan Klein, University of California - Berkeley
Alexandre Bouchard-Côté, University of California - Berkeley
Percy Liang, University of California - Berkeley

Document Type Working Paper

P. Liang, A. Bouchard-Cote,, D. Klein, & B. Taskar (2006). An End-to-End Discriminative Approach to Machine Translation.


We present a perceptron-style discriminative approach to machine translation in which large feature sets can be exploited. Unlike discriminative reranking approaches, our system can take advantage of learned features in all stages of decoding. We first discuss several challenges to error-driven discriminative approaches. In particular, we explore different ways of updating parameters given a training example. We find that making frequent but smaller updates is preferable to making fewer but larger updates. Then, we discuss an array of features and show both how they quantitatively increase BLEU score and how they qualitatively interact on specific examples. One particular feature we investigate is a novel way to introduce learning into the initial phrase extraction process, which has previously been entirely heuristic.


Date Posted: 11 July 2012