Robustness Tests for Automatic Machine Translation Metrics with Adversarial Attacks
Submission Type: Regular Short Paper
Submission Track: Resources and Evaluation
Submission Track 2: Machine Translation
Keywords: Automatic metric, textual adversarial attack, machine translation
Abstract: We investigate MT evaluation metric performance on adversarially-synthesized texts, to shed light on metric robustness. We experiment with word- and character-level attacks on three popular machine translation metrics: BERTScore, BLEURT, and COMET. Our human experiments validate that automatic metrics tend to overpenalize adversarially-degraded translations. We also identify inconsistencies in BERTScore ratings, where it judges the original sentence and the adversarially-degraded one as similar, while judging the degraded translation as notably worse than the original with respect to the reference. We identify patterns of brittleness that motivate more robust metric development.
Submission Number: 3240
Loading