A block bigram prediction model for statistical machine translation

A block bigram prediction model for statistical machine translation (2007)

Cached

Download Links

[stat.rutgers.edu]

Other Repositories/Bibliography

DBLP

by Christoph Tillmann , Tong Zhang

Venue:	ACM Transactions Speech Language Processing
Citations:	3 - 1 self

Versions

Version History

Metadata Version 1

Datum	Value	Source
TITLE	A block bigram prediction model for statistical machine translation	INFERENCE
AUTHOR NAME	Christoph Tillmann	SVM HeaderParse 0.2
AUTHOR AFFIL	IBM T.J. Watson Research Center; and	SVM HeaderParse 0.2
AUTHOR NAME	Tong Zhang	SVM HeaderParse 0.2
AUTHOR AFFIL	Yahoo Research	SVM HeaderParse 0.2
ABSTRACT	In this paper, we present a novel training method for a localized phrase-based prediction model for statistical machine translation (SMT). The model predicts block neighbors to carry out a phrasebased translation that explicitly handles local phrase re-ordering. We use a maximum likelihood criterion to train a log-linear block bigram model which uses real-valued features (e.g. a language model score) as well as binary features based on the block identities themselves (e.g. block bigram features). The model training relies on an efficient enumeration of local block neighbors in parallel training data. A novel stochastic gradient descent (SGD) training algorithm is presented that can easily handle millions of features. Moreover, when viewing SMT as a block generation process, it becomes quite similar to sequential natural language annotation problems such as part-of-speech tagging, phrase chunking, or shallow parsing. The novel approach is successfully tested on a standard Arabic-English translation task using two different phrase re-ordering models: a block orientation model and a phrase-distortion model. Categories and Subject Descriptors: I.2.7 [Artificial Intelligence]: Natural Language Processing—statistical machine translation; G.3 [Probability and Statistics]: Statistical computing— stochastic gradient descent	SVM HeaderParse 0.2
YEAR	2007	INFERENCE
VENUE	ACM Transactions Speech Language Processing	INFERENCE
VENUE TYPE	JOURNAL	INFERENCE
VOLUME	4	INFERENCE
CITATIONS	42 found	ParsCit 1.0