Re-evaluating the Role of BLEU in Machine Translation Research Export

@misc{citeulike:904418, 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.}, author = {Burch, Chris C. and Osborne, Miles and Koehn, Philipp}, citeulike-article-id = {904418}, citeulike-linkout-0 = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.60.8116}, keywords = {general, mt-eval}, posted-at = {2006-10-19 04:46:25}, priority = {2}, title = {Re-evaluating the Role of BLEU in Machine Translation Research}, url = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.60.8116} }

TY - GEN ID - citeulike:904418 L3 - citeulike-article-id:904418 N2 - 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. TI - Re-evaluating the Role of BLEU in Machine Translation Research KW - general KW - mt-eval AU - Burch, Chris AU - Osborne, Miles AU - Koehn, Philipp UR - http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.60.8116 ER -