Stochastic iterative alignment for machine translation evaluation

Stochastic iterative alignment for machine translation evaluation (2006)

by Ding Liu , Daniel Gildea

Venue:	In COLING/ACL-06 Poster
Citations:	4 - 0 self

Datum	Value	Source
TITLE	Stochastic iterative alignment for machine translation evaluation	INFERENCE
AUTHOR NAME	Ding Liu	SVM HeaderParse 0.2
AUTHOR AFFIL	Department of Computer Science; University of Rochester	SVM HeaderParse 0.2
AUTHOR ADDR	Rochester, NY 14627	SVM HeaderParse 0.2
AUTHOR NAME	Daniel Gildea	SVM HeaderParse 0.2
AUTHOR AFFIL	Department of Computer Science; University of Rochester	SVM HeaderParse 0.2
AUTHOR ADDR	Rochester, NY 14627	SVM HeaderParse 0.2
ABSTRACT	A number of metrics for automatic evaluation of machine translation have been proposed in recent years, with some metrics focusing on measuring the adequacy of MT output, and other metrics focusing on fluency. Adequacy-oriented metrics such as BLEU measure n-gram overlap of MT outputs and their references, but do not represent sentence-level information. In contrast, fluency-oriented metrics such as ROUGE-W compute longest common subsequences, but ignore words not aligned by the LCS. We propose a metric based on stochastic iterative string alignment (SIA), which aims to combine the strengths of both approaches. We compare SIA with existing metrics, and find that it outperforms them in overall evaluation, and works specially well in fluency evaluation. 1	SVM HeaderParse 0.2
YEAR	2006	INFERENCE
VENUE	In COLING/ACL-06 Poster	INFERENCE
VENUE TYPE	CONFERENCE	INFERENCE
CITATIONS	10 found	ParsCit 1.0