We study the problem of response selection for multi-turn conversation in retrieval-based chatbots. The task involves matching a response candidate with a conversation context, the challenges for which include how to recognize important parts of the context, and how to model the relationships among utterances in the context. Existing matching methods may lose important information in contexts as we can interpret them with a unified framework in which contexts are transformed to fixed-length vectors without any interaction with responses before matching. This motivates us to propose a new matching framework that can sufficiently carry important information in contexts to matching and model relationships among utterances at the same time. The new framework, which we call a sequential matching framework (SMF), lets each utterance in a context interact with a response candidate at the first step and transforms the pair to a matching vector. The matching vectors are then accumulated following the order of the utterances in the context with a recurrent neural network (RNN) that models relationships among utterances. Context-response matching is then calculated with the hidden states of the RNN. Under SMF, we propose a sequential convolutional network and sequential attention network and conduct experiments on two public data sets to test their performance. Experiment results show that both models can significantly outperform state-of-the-art matching methods. We also show that the models are interpretable with visualizations that provide us insights on how they capture and leverage important information in contexts for matching.

中文翻译：

---

基于检索的聊天机器人中多轮响应选择的顺序匹配框架

我们研究了基于检索的聊天机器人中多轮对话的响应选择问题。该任务涉及将响应候选与对话上下文相匹配，其挑战包括如何识别上下文的重要部分，以及如何对上下文中话语之间的关系进行建模。现有的匹配方法可能会丢失上下文中的重要信息，因为我们可以用一个统一的框架来解释它们，在该框架中，上下文被转换为固定长度的向量，而在匹配之前不与响应进行任何交互。这促使我们提出一种新的匹配框架，该框架可以充分携带上下文中的重要信息，同时匹配和建模话语之间的关系。新框架，我们称之为顺序匹配框架（SMF），让上下文中的每个话语在第一步与响应候选者交互，并将该对转换为匹配向量。然后，匹配向量按照上下文中话语的顺序与循环神经网络 (RNN) 一起累积，该网络对话语之间的关系进行建模。然后使用 RNN 的隐藏状态计算上下文响应匹配。在 SMF 下，我们提出了顺序卷积网络和顺序注意网络，并在两个公共数据集上进行实验以测试其性能。实验结果表明，这两种模型都可以显着优于最先进的匹配方法。我们还展示了这些模型可以通过可视化来解释，这些可视化为我们提供了关于它们如何捕获和利用上下文中的重要信息进行匹配的见解。