Word-level confidence estimation for machine translation using phrase-based translation models

Word-level confidence estimation for machine translation using phrase-based translation models (2005)

Cached

Download Links

[www.tc-star.org]
[acl.ldc.upenn.edu]
[www.aclweb.org]

Other Repositories/Bibliography

DBLP

by Nicola Ueffing , Hermann Ney

Venue:	Computational Linguistics
Citations:	27 - 3 self

Versions

Version History

Metadata Version 1

Datum	Value	Source
TITLE	Word-level confidence estimation for machine translation using phrase-based translation models	INFERENCE
AUTHOR NAME	Nicola Ueffing	SVM HeaderParse 0.2
AUTHOR AFFIL	Lehrstuhl für Informatik VI, Computer Science Department; RWTH Aachen University	SVM HeaderParse 0.2
AUTHOR ADDR	D-52056 Aachen, Germany	SVM HeaderParse 0.2
AUTHOR NAME	Hermann Ney	SVM HeaderParse 0.2
AUTHOR AFFIL	Lehrstuhl für Informatik VI, Computer Science Department; RWTH Aachen University	SVM HeaderParse 0.2
AUTHOR ADDR	D-52056 Aachen, Germany	SVM HeaderParse 0.2
ABSTRACT	Confidence measures for machine translation is a method for labeling each word in an automatically generated translation as correct or incorrect. In this paper, we will present a new approach to confidence estimation which has the advantage that it does not rely on system output such as Nbest lists or word graphs as many other confidence measures do. It is, thus, applicable to any kind of machine translation system. Experimental evaluation has been performed on translation of technical manuals in three different language pairs. Results will be presented for different machine translation systems to show that the new approach is independent of the underlying machine translation system which generated the translations. To the best of our knowledge, the performance of the new confidence measure is better than that of any existing confidence measure. 1	SVM HeaderParse 0.2
YEAR	2005	INFERENCE
VENUE	Computational Linguistics	INFERENCE
VENUE TYPE	CONFERENCE	INFERENCE
PAGES	763--770	INFERENCE
VOLUME	33	INFERENCE
CITATIONS	7 found	ParsCit 1.0