Emily: Developing An Emotion-affective Open-Domain Chatbot with Knowledge Graph-based Persona

In this paper, we describe approaches for developing Emily, an emotion-affective opendomain chatbot. Emily can perceive a user’s negative emotion state and offer supports by positively converting the user’s emotion states. This is done by finetuning a pretrained dialogue model upon data capturing dialogue contexts and desirable emotion states transition across turns. Emily can differentiate a general open-domain dialogue utterance with questions relating to personal information. By leveraging a question-answering approach based on knowledge graphs to handle personal information, Emily maintains personality consistency. We evaluate Emily against a few state-of-the-art open-domain chatbots and show the effects of the proposed approaches in emotion affecting and addressing personality inconsistency.

[1]  Rico Sennrich,et al.  Improving Neural Machine Translation Models with Monolingual Data , 2015, ACL.

[2]  Satoshi Nakamura,et al.  Positive Emotion Elicitation in Chat-Based Dialogue Systems , 2019, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

[3]  William Yang Wang,et al.  MojiTalk: Generating Emotional Responses at Scale , 2017, ACL.

[4]  Jason Weston,et al.  Translating Embeddings for Modeling Multi-relational Data , 2013, NIPS.

[5]  Satoshi Nakamura,et al.  Eliciting Positive Emotion through Affect-Sensitive Dialogue Response Generation: A Neural Network Approach , 2018, AAAI.

[6]  Jingyuan Zhang,et al.  Knowledge Graph Embedding Based Question Answering , 2019, WSDM.

[7]  Ruslan Salakhutdinov,et al.  Open Domain Question Answering Using Early Fusion of Knowledge Bases and Text , 2018, EMNLP.

[8]  Song Liu,et al.  Personalized Dialogue Generation with Diversified Traits , 2019, ArXiv.

[9]  Le Song,et al.  Variational Reasoning for Question Answering with Knowledge Graph , 2017, AAAI.

[10]  Omer Levy,et al.  RoBERTa: A Robustly Optimized BERT Pretraining Approach , 2019, ArXiv.

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

[12]  William W. Cohen,et al.  PullNet: Open Domain Question Answering with Iterative Retrieval on Knowledge Bases and Text , 2019, EMNLP.

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

[14]  Ming-Wei Chang,et al.  BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.

[15]  Huaiyu Zhu.  On Information and Sufficiency , 1997 .

[16]  Mary Williamson,et al.  Recipes for Building an Open-Domain Chatbot , 2020, EACL.

[17]  Peng Xu,et al.  MoEL: Mixture of Empathetic Listeners , 2019, EMNLP.

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

[19]  Xiaoyan Zhu,et al.  Assigning personality/identity to a chatting machine for coherent conversation generation , 2017, ArXiv.

[20]  Y-Lan Boureau,et al.  Towards Empathetic Open-domain Conversation Models: A New Benchmark and Dataset , 2018, ACL.

[21]  Haoyu Song,et al.  Profile Consistency Identification for Open-domain Dialogue Agents , 2020, EMNLP.

[22]  Zhen Guo,et al.  PLATO-2: Towards Building an Open-Domain Chatbot via Curriculum Learning , 2020, ArXiv.

[23]  Pascale Fung,et al.  HappyBot: Generating Empathetic Dialogue Responses by Improving User Experience Look-ahead , 2019, ArXiv.

[24]  Xiaoyan Zhu,et al.  Emotional Chatting Machine: Emotional Conversation Generation with Internal and External Memory , 2017, AAAI.

[25]  Daling Wang,et al.  EmoElicitor: An Open Domain Response Generation Model with User Emotional Reaction Awareness , 2020, IJCAI.

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

[27]  Apoorv Saxena,et al.  Improving Multi-hop Question Answering over Knowledge Graphs using Knowledge Base Embeddings , 2020, ACL.

[28]  Zhou Yu,et al.  Towards Emotional Support Dialog Systems , 2021, ACL.

[29]  Erik Nijkamp,et al.  Towards Holistic and Automatic Evaluation of Open-Domain Dialogue Generation , 2020, ACL.

[30]  Guillaume Bouchard,et al.  Complex Embeddings for Simple Link Prediction , 2016, ICML.