Conference icon

Conference

A Discriminative Latent Variable Model for Statistical Machine Translation.

Abstract:

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 derivation...

Expand abstract

Actions


Authors


More by this author
Institution:
University of Oxford
Department:
Oxford, MPLS, Computer Science
Osborne, M More by this author

Contributors

Role:
Editor
Role:
Editor
Role:
Editor
Role:
Editor
Role:
Editor
Publisher:
The Association for Computer Linguistics Publisher's website
Pages:
200-208
Publication date:
2008
URN:
uuid:4a44c3a3-e958-4625-8f6f-d49e6b2c4d82
Source identifiers:
328115
Local pid:
pubs:328115
ISBN:
978-1-932432-04-6

Terms of use


Metrics



If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP