A Sequential Matching Framework for Multi-Turn Response Selection in Retrieval-Based Chatbots

A Sequential Matching Framework for Multi-Turn Response Selection in Retrieval-Based Chatbots Yu Wu Beihang University State Key Laboratory of Software Development Environment wuyu@buaa.edu.cn Wei Wu Microsoft Corporation Research and AI Group wuwei@microsoft.com Chen Xing NanKai University College of Computer and Control Engineering xingchen1113@gmail.com Can Xu Microsoft Corporation Research and AI Group can.xu@microsoft.com Zhoujun Li Beihang University State Key Laboratory of Software Development Environment lizj@buaa.edu.cn Ming Zhou Microsoft Research Natural Language Computing Group mingzhou@microsoft.com Submission received: 14 August 2017; revised version received: 3 July 2018; accepted for publication: 6 December 2018. doi:10.1162/COLI a 00345 © 2019 Association for Computational Linguistics Published under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0) license Computational Linguistics Volume 45, Number 1 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. 1. Introduction Recent years have witnessed a surge of interest on building conversational agents both in industry and academia. Existing conversational agents can be categorized into task- oriented dialog systems and non–task-oriented chatbots. Dialog systems focus on help- ing people complete specific tasks in vertical domains (Young et al. 2010), such as flight booking, bus route enquiry, restaurant recommendation, and so forth; chatbots aim to naturally and meaningfully converse with humans on open domain topics (Ritter, Cherry, and Dolan 2011). Building an open domain chatbot is challenging, because it requires the conversational engine to be capable of responding to any input from humans that covers a wide range of topics. To address the problem, researchers have considered leveraging the large amount of conversation data available on the Internet, and proposed generation-based methods (Shang, Lu, and Li 2015; Vinyals and Le …

Content truncated to 500 words