BLEUÂTRE: flattening syntactic dependencies for MT evaluation

This paper describes a novel approach to syntactically-informed evaluation of machine translation (MT). Using a statistical, treebanktrained parser, we extract word-word dependencies from reference translations and then compile these dependencies into a representation that allows candidate translations to be evaluated by string comparisons, as is done in n-gram approaches to MT evaluation. This approach gains the benefit of syntactic analysis of the reference translations, but avoids the need to parse potentially noisy candidate translations. Preliminary experiments using 15,242 judgments of reference-candidate pairs from translations of Chinese newswire text show that the correlation of our approach with human judgments is only slightly lower than other reported results. With the addition of multiple reference translations, however, performance improves markedly. These results are encouraging, especially given that our system is a prototype and makes no essential use of synonymy, paraphrasing or inflectional morphological information, all of which would be easy to add.