Two-stage Behavior Cloning for Spoken Dialogue System in Debt Collection

With the rapid growth of internet finance and the booming of financial lending, the intelligent calling for debt collection in FinTech companies has driven increasing attention. Nowadays, the widely used intelligent calling system is based on dialogue flow, namely configuring the interaction flow with the finite-state machine. In our scenario of debt collection, the completed dialogue flow contains more than one thousand interactive paths. All the dialogue procedures are artificially specified, with extremely high maintenance costs and error-prone. To solve this problem, we propose the behaviorcloning-based collection robot framework without any dialogue flow configuration, called two-stage behavior cloning (TSBC). In the first stage, we use multi-label classification model to obtain policies that may be able to cope with the current situation according to the dialogue state; in the second stage, we score several scripts under each obtained policy to select the script with the highest score as the reply for the current state. This framework makes full use of the massive manual collection records without labeling and fully absorbs artificial wisdom and experience. We have conducted extensive experiments in both single-round and multi-round scenarios and showed the effectiveness of the proposed system. The accuracy of a single round of dialogue can be improved by 5%, and the accuracy of multiple rounds of dialogue can be increased by 3.1%.

[1]  Oussama Khatib,et al.  Springer Handbook of Robotics , 2007, Springer Handbooks.

[2]  Joelle Pineau,et al.  Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models , 2015, AAAI.

[3]  Lalit R. Bahl,et al.  Maximum mutual information estimation of hidden Markov model parameters for speech recognition , 1986, ICASSP '86. IEEE International Conference on Acoustics, Speech, and Signal Processing.

[4]  Jiliang Tang,et al.  A Survey on Dialogue Systems: Recent Advances and New Frontiers , 2017, SKDD.

[5]  Ying Chen,et al.  Multi-Turn Response Selection for Chatbots with Deep Attention Matching Network , 2018, ACL.

[6]  Alexander Dekhtyar,et al.  Information Retrieval , 2018, Lecture Notes in Computer Science.

[7]  Maxine Eskénazi,et al.  Towards End-to-End Learning for Dialog State Tracking and Management using Deep Reinforcement Learning , 2016, SIGDIAL Conference.

[8]  Michael F. McTear,et al.  Modelling spoken dialogues with state transition diagrams: experiences with the CSLU toolkit , 1998, ICSLP.

[9]  Michael I. Jordan,et al.  Advances in Neural Information Processing Systems 30 , 1995 .

[10]  Jianfeng Gao,et al.  A Diversity-Promoting Objective Function for Neural Conversation Models , 2015, NAACL.

[11]  David Vandyke,et al.  A Network-based End-to-End Trainable Task-oriented Dialogue System , 2016, EACL.

[12]  Hang Li,et al.  Neural Responding Machine for Short-Text Conversation , 2015, ACL.

[13]  Jihie Kim,et al.  A Study on Dialogue Reward Prediction for Open-Ended Conversational Agents , 2018, ArXiv.

[14]  Peter Bakker,et al.  Robot see, robot do: An overview of robot imitation , 1996 .

[15]  David Yarowsky,et al.  Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing , 2013, EMNLP 2013.

[16]  Stefan Schaal,et al.  Is imitation learning the route to humanoid robots? , 1999, Trends in Cognitive Sciences.

[17]  Zhoujun Li,et al.  Building Task-Oriented Dialogue Systems for Online Shopping , 2017, AAAI.