SAO WMT19 Test Suite: Machine Translation of Audit Reports
This work highlights domain-specific challenges in machine translation for audit reports, showing incremental improvements in evaluation methods but limited practical impact.
The paper introduced a machine translation test set for audit reports and evaluated current MT systems, finding they perform well on surface-level translation but require deep domain knowledge for factual accuracy, with automatic evaluation being ineffective for detecting semantic errors.
This paper describes a machine translation test set of documents from the auditing domain and its use as one of the "test suites" in the WMT19 News Translation Task for translation directions involving Czech, English and German. Our evaluation suggests that current MT systems optimized for the general news domain can perform quite well even in the particular domain of audit reports. The detailed manual evaluation however indicates that deep factual knowledge of the domain is necessary. For the naked eye of a non-expert, translations by many systems seem almost perfect and automatic MT evaluation with one reference is practically useless for considering these details. Furthermore, we show on a sample document from the domain of agreements that even the best systems completely fail in preserving the semantics of the agreement, namely the identity of the parties.