Online large-margin training for statistical machine translation

Watanabe Taro, Jun Suzuki, Tsukada Hajime, Isozaki Hideki

Research output: Contribution to conferencePaperpeer-review

97 Citations (Scopus)

Abstract

We achieved a state of the art performance in statistical machine translation by using a large number of features with an online large-margin training algorithm. The millions of parameters were tuned only on a small development set consisting of less than 1K sentences. Experiments on Arabic-to- English translation indicated that a model trained with sparse binary features outperformed a conventional SMT system with a small number of features.

Original languageEnglish
Pages764-773
Number of pages10
Publication statusPublished - 2007 Dec 1
Externally publishedYes
Event2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, EMNLP-CoNLL 2007 - Prague, Czech Republic
Duration: 2007 Jun 282007 Jun 28

Other

Other2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, EMNLP-CoNLL 2007
CountryCzech Republic
CityPrague
Period07/6/2807/6/28

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Computer Science Applications
  • Information Systems

Fingerprint Dive into the research topics of 'Online large-margin training for statistical machine translation'. Together they form a unique fingerprint.

Cite this