Sampling alignment structure under a Bayesian translation model

Sampling alignment structure under a Bayesian translation model (2008)

by John Denero , Re Bouchard-côté , Dan Klein

Venue:	In Empirical Methods in Natural Language Processing (EMNLP
Citations:	17 - 3 self

Datum	Value	Source
TITLE	Sampling alignment structure under a Bayesian translation model	INFERENCE
AUTHOR NAME	John Denero	SVM HeaderParse 0.2
AUTHOR AFFIL	Computer Science Department; University of California, Berkeley	SVM HeaderParse 0.2
AUTHOR NAME	Re Bouchard-côté	SVM HeaderParse 0.2
AUTHOR AFFIL	Computer Science Department; University of California, Berkeley	SVM HeaderParse 0.2
AUTHOR NAME	Dan Klein	SVM HeaderParse 0.2
AUTHOR AFFIL	Computer Science Department; University of California, Berkeley	SVM HeaderParse 0.2
ABSTRACT	We describe the first tractable Gibbs sampling procedure for estimating phrase pair frequencies under a probabilistic model of phrase alignment. We propose and evaluate two nonparametric priors that successfully avoid the degenerate behavior noted in previous work, where overly large phrases memorize the training data. Phrase table weights learned under our model yield an increase in BLEU score over the word-alignment based heuristic estimates used regularly in phrasebased translation systems. 1	SVM HeaderParse 0.2
YEAR	2008	INFERENCE
VENUE	In Empirical Methods in Natural Language Processing (EMNLP	INFERENCE
VENUE TYPE	CONFERENCE	INFERENCE
PAGES	314--323	INFERENCE
CITATIONS	22 found	ParsCit 1.0