Paper Info
Title
The TALP-UPC Ngram-based statistical machine translation system for ACL-WMT 2008
Abstract
This paper reports on the participation of the TALP Research Center of the UPC (Universitat Politècnica de Catalunya) to the ACL WMT 2008 evaluation campaign. This year's system is the evolution of the one we employed for the 2007 campaign. Main updates and extensions involve linguistically motivated word reordering based on the reordering patterns technique. In addition, this system introduces a target language model, based on linguistic classes (Part-of-Speech), morphology reduction for an inflectional language (Spanish) and an improved optimization procedure. Results obtained over the development and test sets on Spanish to English (and the other way round) translations for both the traditional Europarl and a challenging News stories tasks are analyzed and commented.
Year
Venue
Keywords
2008
WMT@ACL
reordering patterns technique,statistical machine translation system,universitat polit,improved optimization procedure,target language model,evaluation campaign,challenging news stories task,talp research center,linguistically motivated word reordering,inflectional language,acl wmt,part of speech
Field
DocType
Citations 
Research center,Computer science,Machine translation system,Speech recognition,Natural language processing,Artificial intelligence,Language model
Conference
3
PageRank 
References 
Authors
0.51
11
9
Name
Order
Citations
PageRank
Maxim Khalilov18012.71
Adolfo Hernández H.260.99
Marta R. Costa-Jussà33913.51
Josep Maria Crego423515.53
Carlos A. Henríquez Q.5182.48
Patrik Lambert627723.36
José A. R. Fonollosa741051.32
José B. Mariño851064.66
Rafael E. Banchs956663.64