An end-to-end discriminative approach to machine translation

  • Authors:

  • Percy Liang;Alexandre Bouchard-Côté;Dan Klein;Ben Taskar

  • Affiliations:

  • University of California at Berkeley, Berkeley, CA;University of California at Berkeley, Berkeley, CA;University of California at Berkeley, Berkeley, CA;University of California at Berkeley, Berkeley, CA

  • Venue:
  • ACL-44 Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the Association for Computational Linguistics
  • Year:
  • 2006

Quantified Score

Hi-index 0.00

Visualization

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.