A human judgment corpus and a metric for Arabic MT evaluation

Abstract

We present a human judgments dataset and an adapted metric for evaluation of Arabic machine translation. Our mediumscale dataset is the first of its kind for Arabic with high annotation quality. We use the dataset to adapt the BLEU score for Arabic. Our score (AL-BLEU) provides partial credits for stem and morphological matchings of hypothesis and reference words. We evaluate BLEU, METEOR and AL-BLEU on our human judgments corpus and show that AL-BLEU has the highest correlation with human judgments. We are releasing the dataset and software to the research community.