Locally training the log-linear model for SMT

  • Authors:

  • Lemao Liu;Hailong Cao;Taro Watanabe;Tiejun Zhao;Mo Yu;CongHui Zhu

  • Affiliations:

  • Harbin Institute of Technology, Harbin, China;Harbin Institute of Technology, Harbin, China;National Institute of Information and Communication Technology, Soraku-gun, Kyoto, Japan;Harbin Institute of Technology, Harbin, China;Harbin Institute of Technology, Harbin, China;Harbin Institute of Technology, Harbin, China

  • Venue:
  • EMNLP-CoNLL '12 Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

In statistical machine translation, minimum error rate training (MERT) is a standard method for tuning a single weight with regard to a given development data. However, due to the diversity and uneven distribution of source sentences, there are two problems suffered by this method. First, its performance is highly dependent on the choice of a development set, which may lead to an unstable performance for testing. Second, translations become inconsistent at the sentence level since tuning is performed globally on a document level. In this paper, we propose a novel local training method to address these two problems. Unlike a global training method, such as MERT, in which a single weight is learned and used for all the input sentences, we perform training and testing in one step by learning a sentence-wise weight for each input sentence. We propose efficient incremental training methods to put the local training into practice. In NIST Chinese-to-English translation tasks, our local training method significantly outperforms MERT with the maximal improvements up to 2.0 BLEU points, meanwhile its efficiency is comparable to that of the global method.