Rethinking Round-trip Translation for Machine Translation Evaluation

Anonymous

Keywords: machine translation evaluation

Abstract: Automatic evaluation on low-resource language translation suffers from a deficiency of parallel corpora. Round-trip translation could be served as a clever and straightforward technique to alleviate the requirement of the parallel evaluation corpus. However, there was an observation of negative correlations between the evaluation scores by forward and round-trip translations in the era of statistical machine translation (SMT).In this paper, we first revisit the round-trip translation evaluation and unveil its long-standing misunderstanding is essentially caused by copying mechanism. After removing copying mechanism in SMT, round-trip translation scores can reflect the forward translation performance. Then, we demonstrate the rectification is overdue as round-trip translation could benefit multiple machine translation evaluation tasks. To be more specific, round-trip translation could be used i) to predict corresponding forward translation scores; ii) to identify adversarial competitors in shared tasks via cross-system verification; and iii) to improve the performance of the recently advanced quality estimation model.

Paper Type: long

Research Area: Machine Translation