Date of Original Version

6-2013

Type

Conference Proceeding

Journal Title

Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

First Page

644

Last Page

649

Rights Management

Copyright 2013 ACL

Abstract or Description

We present a simple log-linear reparameterization of IBM Model 2 that overcomes problems arising from Model 1’s strong assumptions and Model 2’s overparameterization. Efficient inference, likelihood evaluation, and parameter estimation algorithms are provided. Training the model is consistently ten times faster than Model 4. On three large-scale translation tasks, systems built using our alignment model outperform IBM Model 4.

An open-source implementation of the alignment model described in this paper is available from http://github.com/clab/fast align .

Share

COinS
 

Published In

Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 644-649.