Date of Original Version
Proceedings of the Annual Meeting of the Association for Computational Linguistics
Copyright 2011 ACL
Abstract or Description
We introduce a discriminatively trained, globally normalized, log-linear variant of the lexical translation models proposed by Brown et al. (1993). In our model, arbitrary, nonindependent features may be freely incorporated, thereby overcoming the inherent limitation of generative models, which require that features be sensitive to the conditional independencies of the generative process. However, unlike previous work on discriminative modeling of word alignment (which also permits the use of arbitrary features), the parameters in our models are learned from unannotated parallel sentences, rather than from supervised word alignments. Using a variety of intrinsic and extrinsic measures, including translation performance, we show our model yields better alignments than generative baselines in a number of language pairs.
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial-Share Alike 3.0 License.
Proceedings of the Annual Meeting of the Association for Computational Linguistics, 409-419.