论文标题
使用对话依赖关系选择多转向响应选择
Multi-turn Response Selection using Dialogue Dependency Relations
论文作者
论文摘要
多转响应选择是一项旨在开发对话代理的任务。此任务的性能在预训练的语言模型中取得了显着改进。但是，这些模型只是将对话历史记录的转弯串联起来，因为输入和很大程度上忽略了转弯之间的依赖关系。在本文中，我们提出了对话提取算法，将对话历史转换为基于其依赖关系的线程。每个线程都可以视为一个独立的子女图。我们还建议线程编码器模型通过预训练的变压器将线程和候选者编码为紧凑的表示，并最终通过注意力层获得匹配分数。实验表明，依赖关系有助于对话上下文的理解，我们的模型在DSTC7和DSTC8*上都优于最先进的基线，在Ubuntuv2上具有竞争性结果。
Multi-turn response selection is a task designed for developing dialogue agents. The performance on this task has a remarkable improvement with pre-trained language models. However, these models simply concatenate the turns in dialogue history as the input and largely ignore the dependencies between the turns. In this paper, we propose a dialogue extraction algorithm to transform a dialogue history into threads based on their dependency relations. Each thread can be regarded as a self-contained sub-dialogue. We also propose Thread-Encoder model to encode threads and candidates into compact representations by pre-trained Transformers and finally get the matching score through an attention layer. The experiments show that dependency relations are helpful for dialogue context understanding, and our model outperforms the state-of-the-art baselines on both DSTC7 and DSTC8*, with competitive results on UbuntuV2.
