An ngram-based statistical machine translation decoder

An ngram-based statistical machine translation decoder (2005)

by Josep M. Crego , José B. Mariño , Adrià de Gispert

Venue:	PROC. OF THE 9TH EUROPEAN CONFERENCE ON SPEECH COMMUNICATION AND TECHNOLOGY, INTERSPEECH’05
Citations:	12 - 8 self

User correction supplied by mph

Datum	Value	Source
TITLE	An ngram-based statistical machine translation decoder	user correction
AUTHOR NAME	Josep M. Crego	user correction
AUTHOR NAME	José B. Mariño	user correction
AUTHOR NAME	Adrià de Gispert	user correction
ABSTRACT	In this paper we describe MARIE, an Ngram-based statistical machine translation decoder. It is implemented using a beam search strategy, with distortion (or reordering) capabilities. The underlying translation model is based on an Ngram approach, extended to introduce reordering at the phrase level. The search graph structure is designed to perform very accurate comparisons, what allows for a high level of pruning, improving the decoder efficiency. We report several techniques for efficiently prune out the search space. The combinatory explosion of the search space derived from the search graph structure is reduced by limiting the number of reorderings a given translation is allowed to perform, and also the maximum distance a word (or a phrase) is allowed to be reordered. We finally report translation accuracy results on three different translation tasks.	user correction
YEAR	2005	INFERENCE
VENUE	PROC. OF THE 9TH EUROPEAN CONFERENCE ON SPEECH COMMUNICATION AND TECHNOLOGY, INTERSPEECH’05	user correction
VENUE TYPE	CONFERENCE	INFERENCE
PAGES	3193--3196	INFERENCE
CITATIONS	16 found	ParsCit 1.0