Output details
11 - Computer Science and Informatics
University of Edinburgh
Output title
A Discriminative Latent Variable Model for Statistical Machine Translation
Type
E - Conference contribution
DOI
-
Name of conference/published proceedings
Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics (ACL 2008) : Human Language Technologies
Volume number
-
Issue number
-
First page of article
200
ISSN of proceedings
-
Year of publication
2008
Number of additional authors
2
Additional information
<22> Originality: This paper introduces the idea of maximum translation decoding (accounting for competing translations) and shows how statistical machine translation can be made to scale to millions of features. It also shows for the first time how regularisation methods can improve translation.
Significance: Almost all machine translation research uses heuristic methods that are hard to improve. Our approach is based upon a clean machine learning approach which yields a clear agenda for future developments.
Rigour: Uses optimisation on a training set and evaluation on a test set. Paper appeared in the top NLP venue (acceptance rate 25%).
Interdisciplinary
-
Cross-referral requested
-
Research group
D - Institute for Language, Cognition & Computation
Citation count
17
Proposed double-weighted
No
Double-weighted statement
-
Reserve for a double-weighted output
No
Non-English
No
English abstract
-
