Recent studies have shown that the multi-encoder models are agnostic to the choice of context, and the context encoder generates noise which helps improve the models in terms of BLEU score. In this paper, we further explore this idea by evaluating with context-aware pronoun translation test set by training multi-encoder models trained on three different context settings viz, previous two sentences, random two sentences, and a mix of both as context. Specifically, we evaluate the models on the ContraPro test set to study how different contexts affect pronoun translation accuracy. The results show that the model can perform well on the ContraPro test set even when the context is random. We also analyze the source representations to study whether the context encoder generates noise. Our analysis shows that the context encoder provides sufficient information to learn discourse-level information. Additionally, we observe that mixing the selected context (the previous two sentences in this case) and the random context is generally better than the other settings.

翻译：近期研究表明，多编码器模型对上下文的选择具有不可知性，且上下文编码器产生的噪声有助于提升模型的BLEU分数。本文通过使用上下文感知代词翻译测试集，进一步探究这一观点：我们训练了三种不同上下文设置（即前两个句子、随机两个句子以及两者的混合）下的多编码器模型。具体而言，我们在ContraPro测试集上评估模型，研究不同上下文如何影响代词翻译的准确率。结果表明，即便上下文是随机的，模型在ContraPro测试集上仍能表现良好。我们还通过分析源语言表示，探究上下文编码器是否产生噪声。分析表明，上下文编码器提供了足够的信息来学习篇章层面的特征。此外，我们观察到，将所选上下文（此处为前两个句子）与随机上下文混合通常优于其他设置。