Efficient integration of maximum entropy lexicon models within the training of statistical alignment models

Ismael García-Varea, Franz J. Och, Hermann Ney, Francisco Casacuberta


Abstract
Maximum entropy (ME) models have been successfully applied to many natural language problems. In this paper, we show how to integrate ME models efficiently within a maximum likelihood training scheme of statistical machine translation models. Specifically, we define a set of context-dependent ME lexicon models and we present how to perform an efficient training of these ME models within the conventional expectation-maximization (EM) training of statistical translation models. Experimental results are also given in order to demonstrate how these ME models improve the results obtained with the traditional translation models. The results are presented by means of alignment quality comparing the resulting alignments with manually annotated reference alignments.
Anthology ID:
2002.amta-papers.6
Volume:
Proceedings of the 5th Conference of the Association for Machine Translation in the Americas: Technical Papers
Month:
October 8-12
Year:
2002
Address:
Tiburon, USA
Venue:
AMTA
SIG:
Publisher:
Springer
Note:
Pages:
54–63
Language:
URL:
https://link.springer.com/chapter/10.1007/3-540-45820-4_6
DOI:
Bibkey:
Cite (ACL):
Ismael García-Varea, Franz J. Och, Hermann Ney, and Francisco Casacuberta. 2002. Efficient integration of maximum entropy lexicon models within the training of statistical alignment models. In Proceedings of the 5th Conference of the Association for Machine Translation in the Americas: Technical Papers, pages 54–63, Tiburon, USA. Springer.
Cite (Informal):
Efficient integration of maximum entropy lexicon models within the training of statistical alignment models (García-Varea et al., AMTA 2002)
Copy Citation:
PDF:
https://link.springer.com/chapter/10.1007/3-540-45820-4_6