A Survey on Proactive Dialogue Systems: Problems, Methods, and Prospects

Proactive dialogue systems, related to a wide range of real-world conversational applications, equip the conversational agent with the capability of leading the conversation direction towards achieving pre-defined targets or fulfilling certain goals from the system side. It is empowered by advanced techniques to progress to more complicated tasks that require strategical and motivational interactions. In this survey, we provide a comprehensive overview of the prominent problems and advanced designs for conversational agent's proactivity in different types of dialogues. Furthermore, we discuss challenges that meet the real-world application needs but require a greater research focus in the future. We hope that this first survey of proactive dialogue systems can provide the community with a quick access and an overall picture to this practical problem, and stimulate more progresses on conversational AI to the next level.

[1]  Tat-Seng Chua,et al.  PACIFIC: Towards Proactive Conversational Question Answering over Tabular and Textual Data in Finance , 2022, EMNLP.

[2]  Kentaro Inui,et al.  Target-Guided Open-Domain Conversation Planning , 2022, COLING.

[3]  Jianfeng Gao,et al.  OPERA: Harmonizing Task-Oriented Dialogs and Information Seeking Experience , 2022, ACM Transactions on the Web.

[4]  Yejin Choi,et al.  ProsocialDialog: A Prosocial Backbone for Conversational Agents , 2022, EMNLP.

[5]  Jeffrey P. Bigham,et al.  Target-Guided Dialogue Response Generation Using Commonsense and Data Augmentation , 2022, NAACL-HLT.

[6]  William Yang Wang,et al.  KETOD: Knowledge-Enriched Task-Oriented Dialogue , 2022, NAACL-HLT.

[7]  Yangqiu Song,et al.  You Don’t Know My Favorite Color: Preventing Dialogue Representations from Revealing Speakers’ Private Personas , 2022, NAACL.

[8]  Maolin Li,et al.  SalesBot: Transitioning from Chit-Chat to Task-Oriented Dialogues , 2022, ACL.

[9]  Hua Wu,et al.  Where to Go for the Holidays: Towards Mixed-Type Dialogs for Clarification of User Goals , 2022, ACL.

[10]  Tat-Seng Chua,et al.  A Unified Multi-task Learning Framework for Multi-goal Conversational Recommender Systems , 2022, ACM Trans. Inf. Syst..

[11]  Tat-Seng Chua,et al.  Interacting with Non-Cooperative User: A New Paradigm for Proactive Dialogue Policy , 2022, SIGIR.

[12]  Jane A. Yu,et al.  The Moral Integrity Corpus: A Benchmark for Ethical Dialogue Systems , 2022, ACL.

[13]  Zhou Yu,et al.  Seamlessly Integrating Factual Information and Social Content with Persuasive Dialogue , 2022, AACL.

[14]  F. Crestani,et al.  Evaluating Mixed-initiative Conversational Search Systems via User Simulation , 2022, WSDM.

[15]  Zhihua Wei,et al.  Multiple Choice Questions based Multi-Interest Policy Learning for Conversational Recommendation , 2021, WWW.

[16]  Xinyan Zhao,et al.  UniDS: A Unified Dialogue System for Chit-Chat and Task-oriented Dialogues , 2021, DIALDOC.

[17]  Mikhail Burtsev,et al.  Building and Evaluating Open-Domain Dialogue Corpora with Clarifying Questions , 2021, EMNLP.

[18]  E. Cambria,et al.  Fusing task-oriented and open-domain dialogues in conversational agents , 2021, AAAI.

[19]  Chenyan Xiong,et al.  TIAGE: A Benchmark for Topic-Shift Aware Dialog Modeling , 2021, EMNLP.

[20]  Alan Ritter,et al.  Just Say No: Analyzing the Stance of Neural Dialogue Generation in Offensive Contexts , 2021, EMNLP.

[21]  A. Black,et al.  DialoGraph: Incorporating Interpretable Strategy-Graph Networks into Negotiation Dialogues , 2021, ICLR.

[22]  Jason Weston,et al.  Bot-Adversarial Dialogue for Safe Conversational Agents , 2021, NAACL.

[23]  Bolin Ding,et al.  Unified Conversational Recommendation Policy Learning via Graph-based Reinforcement Learning , 2021, SIGIR.

[24]  Ritam Dutt,et al.  ResPer: Computationally Modelling Resisting Strategies in Persuasive Conversations , 2021, EACL.

[25]  Zhou Yu,et al.  Refine and Imitate: Reducing Repetition and Inconsistency in Persuasion Dialogues via Reinforcement Learning and Human Demonstration , 2020, EMNLP.

[26]  Chunyan Miao,et al.  Keyword-Guided Neural Conversational Model , 2020, AAAI.

[27]  Yejin Choi,et al.  Social Chemistry 101: Learning to Reason about Social and Moral Norms , 2020, EMNLP.

[28]  Paul A. Crook,et al.  Adding Chit-Chat to Enhance Task-Oriented Dialogues , 2020, NAACL.

[29]  Karthik Narasimhan,et al.  Improving Dialog Systems for Negotiation with Personality Modeling , 2020, ACL.

[30]  Zheng-Yu Niu,et al.  Enhancing Dialog Coherence with Event Graph Grounded Content Planning , 2020, IJCAI.

[31]  Zheng-Yu Niu,et al.  Towards Conversational Recommendation over Multi-Type Dialogs , 2020, ACL.

[32]  R. Socher,et al.  A Simple Language Model for Task-Oriented Dialogue , 2020, Neural Information Processing Systems.

[33]  Paul N. Bennett,et al.  Generating Clarifying Questions for Information Retrieval , 2020, WWW.

[34]  Xiaodan Liang,et al.  Dynamic Knowledge Routing Network For Target-Guided Open-Domain Conversation , 2020, AAAI.

[35]  Yu Li,et al.  End-to-End Trainable Non-Collaborative Dialog System , 2019, AAAI.

[36]  Alan W Black,et al.  Augmenting Non-Collaborative Dialog Systems with Explicit Semantic and Strategic Dialog History , 2019, ICLR.

[37]  Zhou Yu,et al.  Alternating Recurrent Dialog Model with Large-scale Pre-trained Language Models , 2019, EACL.

[38]  Jason Weston,et al.  Build it Break it Fix it for Dialogue Safety: Robustness from Adversarial Human Attack , 2019, EMNLP.

[39]  W. Bruce Croft,et al.  Asking Clarifying Questions in Open-Domain Information-Seeking Conversations , 2019, SIGIR.

[40]  Zhou Yu,et al.  Persuasion for Good: Towards a Personalized Persuasive Dialogue System for Social Good , 2019, ACL.

[41]  Xiyuan Zhang,et al.  Proactive Human-Machine Conversation with Explicit Conversation Goal , 2019, ACL.

[42]  Eric P. Xing,et al.  Target-Guided Open-Domain Conversation , 2019, ACL.

[43]  Jianfeng Gao,et al.  Challenges in Building Intelligent Open-domain Dialog Systems , 2019, ACM Trans. Inf. Syst..

[44]  Christopher Joseph Pal,et al.  Towards Deep Conversational Recommendations , 2018, NeurIPS.

[45]  Xu Chen,et al.  Towards Conversational Search and Recommendation: System Ask, User Respond , 2018, CIKM.

[46]  Derek Chen,et al.  Decoupling Strategy and Generation in Negotiation Dialogues , 2018, EMNLP.

[47]  Dongyan Zhao,et al.  Smarter Response with Proactive Suggestion: A New Generative Neural Conversation Paradigm , 2018, IJCAI.

[48]  Jason Weston,et al.  Personalizing Dialogue Agents: I have a dog, do you have pets too? , 2018, ACL.

[49]  Xiang Li,et al.  StalemateBreaker: A Proactive Content-Introducing Approach to Automatic Human-Computer Conversation , 2016, IJCAI.

[50]  Asif Ekbal,et al.  Empathetic Persuasion: Reinforcing Empathy and Persuasiveness in Dialogue Systems , 2022, NAACL-HLT.

[51]  Yuexian Hou,et al.  TopKG: Target-oriented Dialog via Global Planning on Knowledge Graph , 2022, COLING.

[52]  Asif Ekbal,et al.  PEPDS: A Polite and Empathetic Persuasive Dialogue System for Charity Donation , 2022, COLING.

[53]  Zhou Yu,et al.  KERS: A Knowledge-Enhanced Framework for Recommendation Dialog Systems with Multiple Subgoals , 2021, EMNLP.

[54]  Siva Reddy,et al.  Abg-CoQA: Clarifying Ambiguity in Conversational Question Answering , 2021, AKBC.

[55]  Manish Shrivastava,et al.  Topic Shift Detection for Mixed Initiative Response , 2021, SIGDIAL.

[56]  Adam M. Grant,et al.  The dynamics of proactivity at work , 2008 .