Neural Machine Translation (NMT) has been widely adopted over recent years due to its advantages on various translation tasks. However, NMT systems can be error-prone due to the intractability of natural languages and the design of neural networks, bringing issues to their translations. These issues could potentially lead to information loss, wrong semantics, and low readability in translations, compromising the usefulness of NMT and leading to potential non-trivial consequences. Although there are existing approaches, such as using the BLEU score, on quality assessment and issue detection for NMT, such approaches face two serious limitations. First, such solutions require oracle translations, i.e., reference translations, which are often unavailable, e.g., in production environments. Second, such approaches cannot pinpoint the issue types and locations within translations. To address such limitations, we propose a new approach aiming to precisely detect issues in translations without requiring oracle translations. Our approach focuses on two most prominent issues in NMT translations by including two detection algorithms. Our experimental results show that our new approach could achieve high effectiveness on real-world datasets. Our successful experience on deploying the proposed algorithms in both the development and production environments of WeChat, a messenger app with over one billion of monthly active users, helps eliminate numerous defects of our NMT model, monitor the effectiveness on real-world translation tasks, and collect in-house test cases, producing high industry impact.
View on arXiv