Paper: Smaller Alignment Models for Better Translations: Unsupervised Word Alignment with the l0-norm

ACL ID P12-1033
Title Smaller Alignment Models for Better Translations: Unsupervised Word Alignment with the l0-norm
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2012
Authors

Two decades after their invention, the IBM word-based translation models, widely avail- able in the GIZA++ toolkit, remain the dom- inant approach to word alignment and an in- tegral part of many statistical translation sys- tems. Although many models have surpassed them in accuracy, none have supplanted them in practice. In this paper, we propose a simple extension to the IBM models: an `0 prior to en- courage sparsity in the word-to-word transla- tion model. We explain how to implement this extension efficiently for large-scale data (also released as a modification to GIZA++) and demonstrate, in experiments on Czech, Ara- bic, Chinese, and Urdu to English translation, significant improvements over IBM Model 4 in both word alignment (up to +6.7 F1) and translation quality (up to +1.4 Bleu...