Evaluate with Confidence Estimation: Machine ranking of translation outputs using grammatical features

Eleftherios Avramidis; Maja Popovic; David Vilar Torres; Aljoscha Burchardt

In: Proceedings of the Sixth Workshop on Statistical Machine Translation. Workshop on Statistical Machine Translation (WMT-11), located at EMNLP, July 30-31, Edinburgh, United Kingdom, Pages 65-70, Association for Computational Linguistics, 7/2011.


We present a pilot study on an evaluation method which is able to rank translation outputs with no reference translation, given only their source sentence. The system employs a statistical classifier trained upon existing human rankings, using several features derived from analysis of both the source and the target sentences. Development experiments on one language pair showed that the method has considerably good correlation with human ranking when using features obtained from a PCFG parser.


Weitere Links

Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence