Paper: A Discriminative Latent Variable Model for Statistical Machine Translation

ACL ID P08-1024
Title A Discriminative Latent Variable Model for Statistical Machine Translation
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2008
Authors

Large-scale discriminative machine transla- tion promises to further the state-of-the-art, but has failed to deliver convincing gains over current heuristic frequency count systems. We argue that a principle reason for this failure is not dealing with multiple, equivalent transla- tions. We present a translation model which models derivations as a latent variable, in both training and decoding, and is fully discrimina- tive and globally optimised. Results show that accounting for multiple derivations does in- deed improve performance. Additionally, we show that regularisation is essential for max- imum conditional likelihood models in order to avoid degenerate solutions.