Paper Info
Title
Ngram-based statistical machine translation enhanced with multiple weighted reordering hypotheses
Abstract
This paper describes the 2007 Ngram-based statistical machine translation system developed at the TALP Research Center of the UPC (Universitat Politècnica de Catalunya) in Barcelona. Emphasis is put on improvements and extensions of the previous years system, being highlyghted and empirically compared. Mainly, these include a novel word ordering strategy based on: (1) statistically monotonizing the training source corpus and (2) a novel reordering approach based on weighted reordering graphs. In addition, this system introduces a target language model based on statistical classes, a feature for out-of-domain units and an improved optimization procedure. The paper provides details of this system participation in the ACL 2007 SECOND WORKSHOP ON STATISTICAL MACHINE TRANSLATION. Results on three pairs of languages are reported, namely from Spanish, French and German into English (and the other way round) for both the in-domain and out-of-domain tasks.
Year
Venue
Keywords
2007
WMT@ACL
multiple weighted reordering hypothesis,second workshop,statistical class,novel reordering approach,ngram-based statistical machine translation,out-of-domain task,novel word,weighted reordering graph,out-of-domain unit,system participation,previous years system
Field
DocType
Citations 
Rule-based machine translation,Research center,Graph,Computer science,Machine translation,Machine translation system,Natural language processing,Artificial intelligence,Language model,Machine learning,German
Conference
5
PageRank 
References 
Authors
0.47
6
7
Name
Order
Citations
PageRank
Marta R. Costa-Jussà13913.51
Josep Maria Crego223515.53
Patrik Lambert327723.36
Maxim Khalilov48012.71
José A. R. Fonollosa541051.32
José B. Mariño651064.66
Rafael E. Banchs756663.64