Dialogue Systems, Chatbots, and Conversational Agents

Introduction

Conversation is the most natural form of interaction between humans, so it is not surprising that it has also been becoming very prominent in human–machine interactions.

This has been driven by recent advances in artificial intelligence, which have enabled us to improve the reliability of intelligent systems.

Example of an interaction between a customer requesting help and an automated agent asking a clarification question

However, dialogue systems can be deployed even if they are not able to fully process all incoming requests. The system can try to answer the request and ask clarifying questions to solicit additional information from the customer. The customer can then seamlessly be transferred over to a human agent. This sort of setup can enable substantial cost savings and also increased customer satisfaction due to reduced waiting times.

Related Publications

For more information, please consult our publications:

Interactive Question Clarification in Dialogue via Reinforcement Learning BibTeX
Xiang Hu, Zujie Wen, Yafang Wang, Xiaolong Li, Gerard de Melo (2020)
In: Proc. COLING 2020 (Industry Track).
Reinforcement Learning over Knowledge Graphs for Explainable Dialogue Intent Mining BibTeX
Kai Yang, Kong Xinyu, Yafang Wang, Jie Zhang, Gerard de Melo (2020)
IEEE Access 8, 2020, p. 85348–85358. IEEE.
Impact factor: 4.098 (2018 JCR)
COOKIE: A Dataset for Conversational Recommendation over Knowledge Graphs in E-Commerce BibTeX
Zuohui Fu, Yikun Xian, Yaxin Zhu, Yongfeng Zhang, Gerard de Melo (2020)
ArXiv 2008.09237, 2020.
Data Augmentation for Multiclass Utterance Classification – A Systematic Study BibTeX
Binxia Xu, Siyuan Qiu, Jie Zhang, Yafang Wang, Xiaoyu Shen, Gerard de Melo (2020)
In: Proc. COLING 2020.

More publications