N-Gram Posterior Probabilities for Statistical Machine Translation

N-Gram Posterior Probabilities for Statistical Machine Translation (2006)

by Richard Zens , Hermann Ney

Venue:	TECHNOLOGY CONFERENCE OF THE NORTH AMERICAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (HLT-NAACL): PROC. OF THE WORKSHOP ON STATISTICAL MACHINE TRANSLATION
Citations:	12 - 1 self

User correction supplied by mph

Datum	Value	Source
TITLE	N-Gram Posterior Probabilities for Statistical Machine Translation	user correction
AUTHOR NAME	Richard Zens	user correction
AUTHOR AFFIL	Human Language Technology and Pattern Recognition; Lehrstuhl für Informatik 6 – Computer Science Department	user correction
AUTHOR ADDR	RWTH Aachen University, D-52056 Aachen, Germany	user correction
AUTHOR NAME	Hermann Ney	user correction
AUTHOR AFFIL	Human Language Technology and Pattern Recognition; Lehrstuhl für Informatik 6 – Computer Science Department	user correction
AUTHOR ADDR	RWTH Aachen University, D-52056 Aachen, Germany	user correction
ABSTRACT	Word posterior probabilities are a common approach for confidence estimation in automatic speech recognition and machine translation. We will generalize this idea and introduce n-gram posterior probabilities and show how these can be used to improve translation quality. Additionally, we will introduce a sentence length model based on posterior probabilities. We will show	user correction
YEAR	2006	INFERENCE
VENUE	TECHNOLOGY CONFERENCE OF THE NORTH AMERICAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (HLT-NAACL): PROC. OF THE WORKSHOP ON STATISTICAL MACHINE TRANSLATION	user correction
VENUE TYPE	CONFERENCE	INFERENCE
CITATIONS	18 found	ParsCit 1.0