Do Not Change Me: On Transferring Entities Without Modification in Neural Machine Translation -- a Multilingual Perspective
This work addresses the problem of entity preservation in machine translation for users relying on accurate translations of technical or personal data, but it is incremental as it focuses on analysis and dataset creation rather than a new method.
The paper investigates the ability of popular neural machine translation models to preserve entities like URLs and emails across four languages, finding that categories such as emojis pose significant challenges. It also introduces a new multilingual synthetic dataset of 36,000 sentences to assess entity transfer quality.
Current machine translation models provide us with high-quality outputs in most scenarios. However, they still face some specific problems, such as detecting which entities should not be changed during translation. In this paper, we explore the abilities of popular NMT models, including models from the OPUS project, Google Translate, MADLAD, and EuroLLM, to preserve entities such as URL addresses, IBAN numbers, or emails when producing translations between four languages: English, German, Polish, and Ukrainian. We investigate the quality of popular NMT models in terms of accuracy, discuss errors made by the models, and examine the reasons for errors. Our analysis highlights specific categories, such as emojis, that pose significant challenges for many models considered. In addition to the analysis, we propose a new multilingual synthetic dataset of 36,000 sentences that can help assess the quality of entity transfer across nine categories and four aforementioned languages.