论文标题
句子级别的人翻译质量估计与基于注意的神经网络
Sentence Level Human Translation Quality Estimation with Attention-based Neural Networks
论文作者
论文摘要
本文探讨了深度学习方法的使用来自动估计人类翻译质量。自动估计可以为翻译教学，检查和质量控制提供有用的反馈。解决此任务的常规方法取决于手动设计的功能和外部知识。本文提出了一个无特色工程的端到端神经模型，并结合了跨注意机制，以检测句子对中哪些部分与评估质量最相关。预测细粒度分数的另一个贡献涉及测量翻译质量不同方面的预测。大型人类注释数据集的经验结果表明，神经模型的表现高于基于特征的方法。数据集和工具可用。
This paper explores the use of Deep Learning methods for automatic estimation of quality of human translations. Automatic estimation can provide useful feedback for translation teaching, examination and quality control. Conventional methods for solving this task rely on manually engineered features and external knowledge. This paper presents an end-to-end neural model without feature engineering, incorporating a cross attention mechanism to detect which parts in sentence pairs are most relevant for assessing quality. Another contribution concerns of prediction of fine-grained scores for measuring different aspects of translation quality. Empirical results on a large human annotated dataset show that the neural model outperforms feature-based methods significantly. The dataset and the tools are available.
