Sciweavers

Share
ACL
2008

A Discriminative Latent Variable Model for Statistical Machine Translation

9 years 1 months ago
A Discriminative Latent Variable Model for Statistical Machine Translation
Large-scale discriminative machine translation 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 translations. We present a translation model which models derivations as a latent variable, in both training and decoding, and is fully discriminative and globally optimised. Results show that accounting for multiple derivations does indeed improve performance. Additionally, we show that regularisation is essential for maximum conditional likelihood models in order to avoid degenerate solutions.
Phil Blunsom, Trevor Cohn, Miles Osborne
Added 29 Oct 2010
Updated 29 Oct 2010
Type Conference
Year 2008
Where ACL
Authors Phil Blunsom, Trevor Cohn, Miles Osborne
Comments (0)
books