A Discriminative Latent Variable Model for Statistical Machine Translation

Phil Blunsom, Trevor Cohn, Miles Osborne

Research output: Chapter in Book/Report/Conference proceedingConference contribution


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.
Original languageEnglish
Title of host publicationProceedings of the 46th Annual Meeting of the Association for Computational Linguistics (ACL 2008)
Subtitle of host publicationHuman Language Technologies
PublisherAssociation for Computational Linguistics
Number of pages9
ISBN (Print)978-1-932432-04-6
Publication statusPublished - 2008


Dive into the research topics of 'A Discriminative Latent Variable Model for Statistical Machine Translation'. Together they form a unique fingerprint.

Cite this