论文标题
重新审视的基线：以上下文感知翻译的方式推动多段模型的限制
A baseline revisited: Pushing the limits of multi-segment models for context-aware translation
论文作者
论文摘要
本文使用多段模型解决了上下文翻译的任务。具体而言，我们表明，增加模型能力进一步推动了这种方法的限制，并且更深的模型更适合捕获上下文依赖性。此外，使用较大模型观察到的改进可以使用知识蒸馏转移到较小的模型中。我们的实验表明，这种方法在几种语言和基准测试中实现了竞争性能，而没有其他特定语言的调整和特定于任务的架构。
This paper addresses the task of contextual translation using multi-segment models. Specifically we show that increasing model capacity further pushes the limits of this approach and that deeper models are more suited to capture context dependencies. Furthermore, improvements observed with larger models can be transferred to smaller models using knowledge distillation. Our experiments show that this approach achieves competitive performance across several languages and benchmarks, without additional language-specific tuning and task specific architectures.
