BJTU-WeChat's Systems for the WMT22 Chat Translation Task
This work addresses chat translation for users needing English-German communication, but it is incremental as it builds on existing methods with specific optimizations.
The paper tackles the WMT'22 chat translation task for English-German by applying Transformer variants with pre-training and fine-tuning techniques, achieving COMET scores of 0.810 and 0.946, which are the highest among all submissions.
This paper introduces the joint submission of the Beijing Jiaotong University and WeChat AI to the WMT'22 chat translation task for English-German. Based on the Transformer, we apply several effective variants. In our experiments, we utilize the pre-training-then-fine-tuning paradigm. In the first pre-training stage, we employ data filtering and synthetic data generation (i.e., back-translation, forward-translation, and knowledge distillation). In the second fine-tuning stage, we investigate speaker-aware in-domain data generation, speaker adaptation, prompt-based context modeling, target denoising fine-tuning, and boosted self-COMET-based model ensemble. Our systems achieve 0.810 and 0.946 COMET scores. The COMET scores of English-German and German-English are the highest among all submissions.