We present the CUNI-Bergamot submission for the WMT22 General translation task. We compete in English$\rightarrow$Czech direction. Our submission further explores block backtranslation techniques. Compared to the previous work, we measure performance in terms of COMET score and named entities translation accuracy. We evaluate performance of MBR decoding compared to traditional mixed backtranslation training and we show a possible synergy when using both of the techniques simultaneously. The results show that both approaches are effective means of improving translation quality and they yield even better results when combined.
翻译:我们为 WMT22 通用翻译任务展示了 CUNI-Bergamot 的提交文件。 我们用捷克的英语进行竞争。 我们的提交文件进一步探索了块状反译技术。 与先前的工作相比, 我们用知识与技术伦理的得分和名称实体的翻译准确性来衡量业绩。 我们比起传统的混合反译培训来评估MBR解码的性能, 同时使用这两种技术时,我们表现出一种可能的协同效应。 结果显示,这两种方法都是提高翻译质量的有效手段,如果加在一起,效果会更好。