论文标题
专注于上下文感知神经机器翻译的串联
Focused Concatenation for Context-Aware Neural Machine Translation
论文作者
论文摘要
对上下文感知的神经机器翻译的一种直接方法在于用连续句子的窗口为标准的编码器架构供给标准的编码器架构，该句子由当前句子形成，以及从其上下文中的许多句子与其串联的句子。在这项工作中，我们提出了一种改进的串联方法，该方法鼓励该模型专注于当前句子的翻译，从而违反了目标上下文产生的损失。我们还提出了一个额外的改进，以加强句子边界的概念和相对句子距离的概念，从而促进模型遵守上下文缩写的目标。我们通过平均翻译质量指标和对比度测试集评估了我们的方法，以转换句子间话语现象，这证明了其优越性对香草串联方法和其他复杂的情境感知系统的优越性。
A straightforward approach to context-aware neural machine translation consists in feeding the standard encoder-decoder architecture with a window of consecutive sentences, formed by the current sentence and a number of sentences from its context concatenated to it. In this work, we propose an improved concatenation approach that encourages the model to focus on the translation of the current sentence, discounting the loss generated by target context. We also propose an additional improvement that strengthen the notion of sentence boundaries and of relative sentence distance, facilitating model compliance to the context-discounted objective. We evaluate our approach with both average-translation quality metrics and contrastive test sets for the translation of inter-sentential discourse phenomena, proving its superiority to the vanilla concatenation approach and other sophisticated context-aware systems.
