Learning Implicit User Profile for Personalized Retrieval-Based Chatbot

In this paper, we explore the problem of developing personalized chatbots. A personalized chatbot is designed as a digital chatting assistant for a user. The key characteristic of a personalized chatbot is that it should have a consistent personality with the corresponding user. It can talk the same way as the user when it is delegated to respond to others' messages. Many methods have been proposed to assign a personality to dialogue chatbots, but most of them utilize explicit user profiles, including several persona descriptions or key-value-based personal information. In a practical scenario, however, users might be reluctant to write detailed persona descriptions, and obtaining a large number of explicit user profiles requires tremendous manual labour. To tackle the problem, we present a retrieval-based personalized chatbot model, namely IMPChat, to learn an implicit user profile from the user's dialogue history. We argue that the implicit user profile is superior to the explicit user profile regarding accessibility and flexibility. IMPChat aims to learn an implicit user profile through modeling user's personalized language style and personalized preferences separately. To learn a user's personalized language style, we elaborately build language models from shallow to deep using the user's historical responses; To model a user's personalized preferences, we explore the conditional relations underneath each post-response pair of the user. The personalized preferences are dynamic and context-aware: we assign higher weights to those historical pairs that are topically related to the current query when aggregating the personalized preferences. We match each response candidate with the personalized language style and personalized preference, respectively, and fuse the two matching signals to determine the final ranking score. We conduct comprehensive experiments on two large datasets, and the results show that our method outperforms all baseline models.

[1]  Zhiyuan Liu,et al.  Convolutional Neural Networks for Soft-Matching N-Grams in Ad-hoc Search , 2018, WSDM.

[2]  Qun Liu,et al.  Syntax-based Deep Matching of Short Texts , 2015, IJCAI.

[3]  Ji-Rong Wen,et al.  Encoding History with Context-aware Representation Learning for Personalized Search , 2020, SIGIR.

[4]  Ji-Rong Wen,et al.  Enhancing Re-finding Behavior with External Memories for Personalized Search , 2020, WSDM.

[5]  Antonella De Angeli,et al.  The unfriendly user: exploring social reactions to chatterbots , 2001 .

[6]  Wei Chu,et al.  AliMe Assist: An Intelligent Assistant for Creating an Innovative E-commerce Experience , 2017, CIKM.

[7]  Alan Ritter,et al.  Data-Driven Response Generation in Social Media , 2011, EMNLP.

[8]  Kellie Morrissey,et al.  'Realness' in Chatbots: Establishing Quantifiable Criteria , 2013, HCI.

[9]  Natalia Gimelshein,et al.  PyTorch: An Imperative Style, High-Performance Deep Learning Library , 2019, NeurIPS.

[10]  Dongyan Zhao,et al.  A Document-grounded Matching Network for Response Selection in Retrieval-based Chatbots , 2019, IJCAI.

[11]  Zhicheng Dou,et al.  ScriptWriter: Narrative-Guided Script Generation , 2020, ACL.

[12]  Zhen-Hua Ling,et al.  Dually Interactive Matching Network for Personalized Response Selection in Retrieval-Based Chatbots , 2019, EMNLP.

[13]  Javier Snaider,et al.  Conversational Contextual Cues: The Case of Personalization and History for Response Ranking , 2016, ArXiv.

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

[15]  Jianfeng Gao,et al.  A Persona-Based Neural Conversation Model , 2016, ACL.

[16]  Zhiyuan Liu,et al.  End-to-End Neural Ad-hoc Ranking with Kernel Pooling , 2017, SIGIR.

[17]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[18]  Marilyn A. Walker,et al.  PERSONAGE: Personality Generation for Dialogue , 2007, ACL.

[19]  Zhicheng Dou,et al.  Content Selection Network for Document-grounded Retrieval-based Chatbots , 2021, ECIR.

[20]  Ji-Rong Wen,et al.  One Chatbot Per Person: Creating Personalized Chatbots based on Implicit User Profiles , 2021, SIGIR.

[21]  Jason Weston,et al.  Key-Value Memory Networks for Directly Reading Documents , 2016, EMNLP.

[22]  Jeffrey Dean,et al.  Efficient Estimation of Word Representations in Vector Space , 2013, ICLR.

[23]  Marco Aurélio Gerosa,et al.  How Should My Chatbot Interact? A Survey on Social Characteristics in Human–Chatbot Interaction Design , 2019, Int. J. Hum. Comput. Interact..

[24]  Zhoujun Li,et al.  Sequential Match Network: A New Architecture for Multi-turn Response Selection in Retrieval-based Chatbots , 2016, ArXiv.

[25]  Joelle Pineau,et al.  The Ubuntu Dialogue Corpus: A Large Dataset for Research in Unstructured Multi-Turn Dialogue Systems , 2015, SIGDIAL Conference.

[26]  Antoine Bordes,et al.  Training Millions of Personalized Dialogue Agents , 2018, EMNLP.

[27]  Jianfeng Gao,et al.  DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation , 2020, ACL.

[28]  Dongyan Zhao,et al.  Modeling Personalization in Continuous Space for Response Generation via Augmented Wasserstein Autoencoders , 2019, EMNLP.

[29]  Alexander I. Rudnicky,et al.  Stochastic Language Generation for Spoken Dialogue Systems , 2000 .

[30]  Ji-Rong Wen,et al.  Group based Personalized Search by Integrating Search Behaviour and Friend Network , 2021, SIGIR.

[31]  Qian Liu,et al.  You Impress Me: Dialogue Generation via Mutual Persona Perception , 2020, ACL.

[32]  Haoyu Song,et al.  Generating Persona Consistent Dialogues by Exploiting Natural Language Inference , 2019, AAAI.

[33]  Alice H. Oh,et al.  Variational Hierarchical User-based Conversation Model , 2019, EMNLP.

[34]  Manuel Portela,et al.  A new friend in our smartphone?: observing interactions with chatbots in the search of emotional engagement , 2017, Interacción.

[35]  Quoc V. Le,et al.  A Neural Conversational Model , 2015, ArXiv.

[36]  Hao Wang,et al.  A Dataset for Research on Short-Text Conversations , 2013, EMNLP.

[37]  Hai Zhao,et al.  Modeling Multi-turn Conversation with Deep Utterance Aggregation , 2018, COLING.

[38]  Hang Li,et al.  Convolutional Neural Network Architectures for Matching Natural Language Sentences , 2014, NIPS.

[39]  Rui Yan,et al.  Learning to Detect Relevant Contexts and Knowledge for Response Selection in Retrieval-based Dialogue Systems , 2020, CIKM.

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

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

[42]  Pan Du,et al.  Proactive Retrieval-based Chatbots based on Relevant Knowledge and Goals , 2021, SIGIR.

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

[44]  Hengpeng Xu,et al.  Speaker or Listener? The Role of a Dialogue Agent , 2020, EMNLP.

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

[46]  Jianfeng Gao,et al.  Neural Approaches to Conversational AI: Question Answering, Task-oriented Dialogues and Social Chatbots , 2019 .

[47]  Harry Shum,et al.  From Eliza to XiaoIce: challenges and opportunities with social chatbots , 2018, Frontiers of Information Technology & Electronic Engineering.

[48]  Chunyuan Yuan,et al.  Multi-hop Selector Network for Multi-turn Response Selection in Retrieval-based Chatbots , 2019, EMNLP.

[49]  Ji-Rong Wen,et al.  Pchatbot: A Large-Scale Dataset for Personalized Chatbot , 2020, SIGIR.

[50]  Haoyu Song,et al.  Generate, Delete and Rewrite: A Three-Stage Framework for Improving Persona Consistency of Dialogue Generation , 2020, ACL.

[51]  Xiaoyan Zhu,et al.  Assigning Personality/Profile to a Chatting Machine for Coherent Conversation Generation , 2018, IJCAI.

[52]  Ji-Rong Wen,et al.  ReBoost: a retrieval-boosted sequence-to-sequence model for neural response generation , 2020, Information Retrieval Journal.

[53]  Dongyan Zhao,et al.  One Time of Interaction May Not Be Enough: Go Deep with an Interaction-over-Interaction Network for Response Selection in Dialogues , 2019, ACL.

[54]  James H. Gerlach,et al.  Understanding Human-Computer Interaction for Information Systems Design , 1991, MIS Q..

[55]  C. Miao,et al.  Towards Persona-Based Empathetic Conversational Models , 2020, EMNLP.