论文标题
神经机器翻译的文档图
Document Graph for Neural Machine Translation
论文作者
论文摘要
先前的工作表明，上下文信息可以改善神经机器翻译（NMT）的性能。但是，大多数现有的文档级NMT方法仅考虑一些以前的句子。如何将整个文档用作全球环境仍然是一个挑战。为了解决这个问题，我们假设可以将文档表示为连接相关上下文的图，而不论其距离如何。我们采用几种类型的关系，包括邻接，句法依赖关系，词汇一致性和核心，来构建文档图。然后，我们将源图和目标图都合并到具有图形卷积网络的常规变压器体系结构中。在包括IWSLT英语，中文英语，WMT英语的各种NMT基准测试的实验 - 俄罗斯 - 俄罗斯 - 俄罗斯，表明，使用文档图可以显着提高翻译质量。广泛的分析验证了文档图是否有利于捕获话语现象。
Previous works have shown that contextual information can improve the performance of neural machine translation (NMT). However, most existing document-level NMT methods only consider a few number of previous sentences. How to make use of the whole document as global contexts is still a challenge. To address this issue, we hypothesize that a document can be represented as a graph that connects relevant contexts regardless of their distances. We employ several types of relations, including adjacency, syntactic dependency, lexical consistency, and coreference, to construct the document graph. Then, we incorporate both source and target graphs into the conventional Transformer architecture with graph convolutional networks. Experiments on various NMT benchmarks, including IWSLT English--French, Chinese-English, WMT English--German and Opensubtitle English--Russian, demonstrate that using document graphs can significantly improve the translation quality. Extensive analysis verifies that the document graph is beneficial for capturing discourse phenomena.
