Paper Info
Title
A maximum entropy approach to syntactic translation rule filtering
Abstract
In this paper we will present a maximum entropy filter for the translation rules of a statistical machine translation system based on tree transducers. This filter can be successfully used to reduce the number of translation rules by more than 70% without negatively affecting translation quality as measured by BLEU. For some filter configurations, translation quality is even improved. Our investigations include a discussion of the relationship of Alignment Error Rate and Consistent Translation Rule Score with translation quality in the context of Syntactic Statistical Machine Translation.
Year
DOI
Venue
2010
10.1007/978-3-642-12116-6_38
CICLing
Keywords
Field
DocType
translation quality,translation rule,statistical machine translation system,tree transducers,maximum entropy approach,filter configuration,maximum entropy filter,syntactic statistical machine translation,consistent translation rule score,alignment error rate,maximum entropy,negative affect
Tree transducers,BLEU,Parse tree,Computer science,Machine translation,Natural language processing,Artificial intelligence,Syntax,Pattern recognition,Word error rate,Filter (signal processing),Speech recognition,Principle of maximum entropy
Conference
Volume
ISSN
ISBN
6008
0302-9743
3-642-12115-2
Citations 
PageRank 
References 
0
0.34
20
Authors
1
Name
Order
Citations
PageRank
Marcin Junczys-Dowmunt131224.24