多语言场景下人类与神经机器翻译的自动判别
Automatic Discrimination of Human and Neural Machine Translation in Multilingual Scenarios
AI总结：
本文研究多语言场景下人类与机器翻译的自动判别，证明源文本融入多语言分类器可提升准确率与跨系统鲁棒性，多源语言训练数据和更长文本序列训练均能进一步改善分类性能。
摘要：
我们致力于解决自动判别人类翻译与机器翻译的任务。与大多数先前工作不同，我们在多语言环境中进行实验，考虑多种语言和多语言预训练语言模型。我们表明，在单一源语言（我们的案例中为德语-英语）的平行数据上训练的分类器，在来自不同源语言的英语翻译上仍能表现良好，即使这些机器翻译是由不同于其训练时所使用的系统生成的。此外，我们证明，与单语分类器相比，在多语言分类器的输入中纳入源文本能够改善（i）其准确率以及（ii）其在跨系统评估上的鲁棒性。进一步地，我们发现使用来自多个源语言（德语、俄语和中文）的训练数据倾向于提高单语和多语言分类器的准确率。最后，我们表明双语分类器和在多个源语言上训练的分类器受益于在更长的文本序列上训练，而非在句子上训练。
英文摘要：
We tackle the task of automatically discriminating between human and machine translations. As opposed to most previous work, we perform experiments in a multilingual setting, considering multiple languages and multilingual pretrained language models. We show that a classifier trained on parallel data with a single source language (in our case German-English) can still perform well on English translations that come from different source languages, even when the machine translations were produced by other systems than the one it was trained on. Additionally, we demonstrate that incorporating the source text in the input of a multilingual classifier improves (i) its accuracy and (ii) its robustness on cross-system evaluation, compared to a monolingual classifier. Furthermore, we find that using training data from multiple source languages (German, Russian, and Chinese) tends to improve the accuracy of both monolingual and multilingual classifiers. Finally, we show that bilingual classifiers and classifiers trained on multiple source languages benefit from being trained on longer text sequences, rather than on sentences.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
