Output details
11 - Computer Science and Informatics
University of Edinburgh
Output title
Stream-based Translation Models for Statistical Machine Translation
Type
E - Conference contribution
DOI
-
Name of conference/published proceedings
Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics
Volume number
-
Issue number
-
First page of article
394
ISSN of proceedings
-
Year of publication
2010
Number of additional authors
2
Additional information
<22> Originality: We are the first people to publish work on streaming and machine translation and this paper represents a continuing line of research. Here we focus on the translation model.
Significance: The original papers (Talbot and Osborne 07a and 07b) became the foundations of what are now standard ways to represent large amounts of data. These methods are used by Google and academic groups (eg ISI, Stuttgart) and are part of the Moses Machine Translation distribution (the world's most dominant academic machine translation system).
Rigour: Uses optimisation on a training set and evaluation on a test set.
Interdisciplinary
-
Cross-referral requested
-
Research group
D - Institute for Language, Cognition & Computation
Citation count
5
Proposed double-weighted
No
Double-weighted statement
-
Reserve for a double-weighted output
No
Non-English
No
English abstract
-
