Статистикалық Машиналық Аударма Семинары
otherentity
ID: statisticalmachinetranslationworkshop
Related Papers
Evaluation without references: IBM1 scores as evaluation metrics
Current metrics for evaluating machine trans- lation quality have the huge drawback that they require human-quality reference transla- tions. We propose a truly automatic evalua- tion metric based on IBM1 …...
Morphemes and POS tags for n-gram based evaluation metrics
We propose the use of morphemes for auto- matic evaluation of machine translation out- put, and systematically investigate a set of F score and BLEU score based metrics calculated on …...
Class error rates for evaluation of machine translation output
We investigate the use of error classification results for automatic evaluation of machine translation output. Five basic error classes are taken into account: morphological errors, syn- tactic (reordering) errors, missing …...