Re-evaluating the role of BLEU in machine translation research

Re-evaluating the role of BLEU in machine translation research (2006)

by Chris Callison-burch , Miles Osborne

Venue:	In EACL
Citations:	53 - 3 self

Datum	Value	Source
TITLE	Re-evaluating the role of BLEU in machine translation research	INFERENCE
AUTHOR NAME	Chris Callison-burch	SVM HeaderParse 0.2
AUTHOR AFFIL	School on Informatics; University of Edinburgh	SVM HeaderParse 0.2
AUTHOR ADDR	2 Buccleuch Place; Edinburgh, EH8 9LW	SVM HeaderParse 0.2
AUTHOR NAME	Miles Osborne	SVM HeaderParse 0.2
AUTHOR AFFIL	School on Informatics; University of Edinburgh	SVM HeaderParse 0.2
AUTHOR ADDR	2 Buccleuch Place; Edinburgh, EH8 9LW	SVM HeaderParse 0.2
ABSTRACT	We argue that the machine translation community is overly reliant on the Bleu machine translation evaluation metric. We show that an improved Bleu score is neither necessary nor sufficient for achieving an actual improvement in translation quality, and give two significant counterexamples to Bleu’s correlation with human judgments of quality. This offers new potential for research which was previously deemed unpromising by an inability to improve upon Bleu scores. 1	SVM HeaderParse 0.2
YEAR	2006	INFERENCE
VENUE	In EACL	INFERENCE
VENUE TYPE	CONFERENCE	INFERENCE
PAGES	249--256	INFERENCE
CITATIONS	6 found	ParsCit 1.0