MT Evaluation

MT: Machine Translation

Overview

Machine translation evaluation studies how well translations preserve meaning and meet linguistic, cultural, and practical needs, helping researchers compare systems and identify failures. Approaches range from reference-based metrics such as BLEU and chrF to neural metrics such as COMET, quality estimation without references, and human assessment using error taxonomies like MQM. Benchmarks increasingly test low-resource languages, specialized domains, document context, cultural nuance, speech, and images, while LLM judges and targeted error checks offer ways to assess qualities that simple text overlap misses. A central challenge is that automatic scores can disagree with human judgments and overlook valid variation, so reliable evaluation must balance scalable metrics with context-sensitive human review.

Latest papers

181 papers10 papers in the last four weeks, down 41% on the four weeks before. 0.1% of all new papers.

Sep 15, 2022

Rethinking Round-Trip Translation for Machine Translation Evaluation

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 obscure correlations between the evaluation scores by forward and round-trip translations in the era of statistical machine translation (SMT). In this paper, we report the surprising finding that round-trip translation can be used for automatic evaluation without the references. Firstly, our revisit on the round-trip translation in SMT evaluation unveils that its long-standing misunderstanding is essentially caused by copying mechanism. After removing copying mechanism in SMT, round-trip translation scores can appropriately 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 improve the performance of the recently advanced quality estimation model; and iii) to identify adversarial competitors in shared tasks via cross-system verification.