Paper: An End-To-End Discriminative Approach To Machine Translation

ACL ID P06-1096
Title An End-To-End Discriminative Approach To Machine Translation
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2006

We present a perceptron-style discriminative ap- proach to machine translation in which large feature sets can be exploited. Unlike discriminative rerank- ing approaches, our system can take advantage of learned features in all stages of decoding. We first discuss several challenges to error-driven discrim- inative approaches. In particular, we explore dif- ferent ways of updating parameters given a training example. We find that making frequent but smaller updates is preferable to making fewer but larger up- dates. Then, we discuss an array of features and show both how they quantitatively increase BLEU score and how they qualitatively interact on spe- cific examples. One particular feature we investi- gate is a novel way to introduce learning into the initial phrase extraction process, w...