An End-to-End Discriminative Approach to Machine Translation

Abstract

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.

Extracted Key Phrases

7 Figures and Tables

0204020072008200920102011201220132014201520162017
Citations per Year

285 Citations

Semantic Scholar estimates that this publication has 285 citations based on the available data.

See our FAQ for additional information.

Cite this paper

@inproceedings{Liang2006AnED, title={An End-to-End Discriminative Approach to Machine Translation}, author={Percy Liang and Alexandre Bouchard-C{\^o}t{\'e} and Dan Klein and Ben Taskar}, booktitle={ACL}, year={2006} }