Reassessing Claims of Human Parity and Super-Human Performance in Machine Translation at WMT 2019

Abstract

We reassess the claims of human parity and super-human performance made at the news shared task of WMT 2019 for three translation directions: English-to-German, English-to-Russian and German-to-English. First we identify three potential issues in the human evaluation of that shared task: (i) the limited amount of intersentential context available, (ii) the limited translation proficiency of the evaluators and (iii) the use of a reference translation. We then conduct a modified evaluation taking these issues into account. Our results indicate that all the claims of human parity and super-human performance made at WMT 2019 should be refuted, except the claim of human parity for English-to-German. Based on our findings, we put forward a set of recommendations and open questions for future assessments of human parity in machine translation.

Accepted at the 22nd Annual Conference of the European Association for Machine Translation (EAMT 2020)

References in corpus (2)

• Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm
• Translationese in Machine Translation Evaluation

Cited by in corpus (1)

• Spinning Language Models: Risks of Propaganda-As-A-Service and Countermeasures