DATScore: Evaluating Translation with Data Augmented Translations

Anonymous

Keywords: Evaluation Metrics, NLG, Machine Translation, NLP, Data Augmentation

Abstract: The rapid development of large pretrained language models not only has revolutionized the field of Natural Language Generation (NLG), but also its evaluation. Inspired by the recent work of BARTScore: a metric leveraging the BART language model to evaluate the quality of generated text from various aspects, we introduce DATScore. DATScore uses data augmentation techniques to improve the evaluation of machine translation. Our main finding is that introducing data augmented translations of the source and reference texts is greatly helpful in evaluating the quality of the generated translation. We also propose two novel score averaging and term weighting strategies to improve the original score computing process of BARTScore. Experimental results on WMT show that DATScore correlates better with human meta-evaluations than the other recent state-of-the-art metrics, especially for low resource languages. Ablation studies demonstrate the value added by our new scoring strategies. Moreover, we report the performance of DATScore on 3 other NLG tasks than translation in our extended experiments.