论文标题
交叉复制网络以进行对话生成
Cross Copy Network for Dialogue Generation
论文作者
论文摘要
在过去的几年中，来自不同领域的观众见证了序列到序列模型的成就（例如LSTM+注意，指针生成器网络和变压器），以增强对话内容的生成。尽管内容流利度和准确性通常是模型培训的主要指标，但对话逻辑（对某些特定领域的关键信息）通常被忽略。以客户服务和法院的辩论对话为例，可以在不同的对话实例中观察到兼容的逻辑，并且这些信息可以为发言提供重要的证据。在本文中，我们提出了一个新颖的网络体系结构 - 交叉复制网络（CCN），以同时探索当前的对话框上下文和类似的对话实例的逻辑结构。法院辩论和客户服务内容生成的两项任务实验证明，所提出的算法优于现有的最新内容生成模型。
In the past few years, audiences from different fields witness the achievements of sequence-to-sequence models (e.g., LSTM+attention, Pointer Generator Networks, and Transformer) to enhance dialogue content generation. While content fluency and accuracy often serve as the major indicators for model training, dialogue logics, carrying critical information for some particular domains, are often ignored. Take customer service and court debate dialogue as examples, compatible logics can be observed across different dialogue instances, and this information can provide vital evidence for utterance generation. In this paper, we propose a novel network architecture - Cross Copy Networks(CCN) to explore the current dialog context and similar dialogue instances' logical structure simultaneously. Experiments with two tasks, court debate and customer service content generation, proved that the proposed algorithm is superior to existing state-of-art content generation models.
