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.
翻译:本文介绍北京桥东大学和WeChat AI联合提交的英文-德文WMT'22聊天翻译任务。 根据变换器,我们应用了几种有效的变式。在实验中,我们使用了培训前的调整模式。在培训前的第一阶段,我们采用了数据过滤和合成数据生成(即反译、前译和知识蒸馏)。在第二个微调阶段,我们调查了语言觉悟的英文-德文数据生成、语音调适、速基背景建模、目标拆分微调和增强的以自我COMET为基础的模型集成。我们的系统达到了0.810和0.946 COMET分数。在提交的所有文件中,ECET英文-德文和德文-英文分数最高。