EMNLPOct, 2021

WeTS: 一个翻译建议的基准测试

TL;DRWe created a benchmark data set called WeTS, which includes human-annotated golden corpus and synthetic corpus to improve the performance of Translation Suggestion (TS) for post editing after machine translation (MT). Our Transformer-based model achieves State-Of-The-Art (SOTA) results on four translation directions: English-to-German, German-to-English, Chinese-to-English and English-to-Chinese.