Bayesian reordering model with feature selection


Alrajeh, Abdullah and Niranjan, Mahesan (2014) Bayesian reordering model with feature selection At ACL2014: The Ninth Workshop on Statistical Machine Translation, United States. 26 - 27 Jun 2014. , pp. 477-485.

Download

[img] PDF wmt14.pdf - Other
Download (423kB)
[img] PDF W14-3361.pdf - Author's Original
Download (231kB)

Description/Abstract

In phrase-based statistical machine translation systems, variation in grammatical structures between source and target languages can cause large movements of phrases. Modeling such movements is crucial in achieving translations of long sentences that appear natural in the target language. We explore generative learning approach to phrase reordering in Arabic to English. Formulating the reordering problem as a classification problem and using naive Bayes with feature selection, we achieve an improvement in the BLEU score over a lexicalized reordering model. The proposed model is compact, fast and scalable to a large corpus.

Item Type: Conference or Workshop Item (Paper)
Venue - Dates: ACL2014: The Ninth Workshop on Statistical Machine Translation, United States, 2014-06-26 - 2014-06-27
Subjects: P Language and Literature > P Philology. Linguistics
Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Organisations: Southampton Wireless Group
ePrint ID: 366149
Date :
Date Event
June 2014Published
Date Deposited: 26 Jun 2014 13:33
Last Modified: 17 Apr 2017 13:37
Further Information:Google Scholar
URI: http://eprints.soton.ac.uk/id/eprint/366149

Actions (login required)

View Item View Item