Title
Soft syntactic constraints for Arabic---English hierarchical phrase-based translation
Abstract
In adding syntax to statistical machine translation, there is a tradeoff between taking advantage of linguistic analysis and allowing the model to exploit parallel training data with no linguistic analysis: translation quality versus coverage. A number of previous efforts have tackled this tradeoff by starting with a commitment to linguistically motivated analyses and then finding appropriate ways to soften that commitment. We present an approach that explores the tradeoff from the other direction, starting with a translation model learned directly from aligned parallel text, and then adding soft constituent-level constraints based on parses of the source language. We argue that in order for these constraints to improve translation, they must be fine-grained: the constraints should vary by constituent type, and by the type of match or mismatch with the parse. We also use a different feature weight optimization technique, capable of handling large amount of features, thus eliminating the bottleneck of feature selection. We obtain substantial improvements in performance for translation from Arabic to English.
Year
DOI
Venue
2012
10.1007/s10590-011-9111-z
Machine Translation
Keywords
Field
DocType
appropriate way,parallel text,feature selection,constituent type,translation quality,statistical machine translation,english hierarchical phrase-based translation,soft syntactic constraint,different feature weight optimization,translation model,parallel training data,linguistic analysis,arabic,machine translation,parsing,syntax
Rule-based machine translation,Example-based machine translation,Computer science,Machine translation,Phrase,Natural language processing,Transfer-based machine translation,Artificial intelligence,Parsing,Dynamic and formal equivalence,Syntax,Linguistics
Journal
Volume
Issue
ISSN
26
1-2
1573-0573
Citations 
PageRank 
References 
7
0.43
45
Authors
3
Name
Order
Citations
PageRank
Yuval Marton143017.90
David Chiang22843144.76
Philip Resnik34352377.99