Emily: Developing An Emotion-affective Open-Domain Chatbot with Knowledge Graph-based Persona
Not on the map. Why?
Abstract (arXiv)
In this paper, we describe approaches for developing Emily, an emotion-affective open-domain 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.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 20 of its 34 references that are in the map. First posted on arXiv 18 Sep 2021.
Builds on
20 of 34 references.
References · 20
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
- 2016Complex Embeddings for Simple Link Predictioncited by 897
- 2019DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generationcited by 842
- 2018Personalizing Dialogue Agents: I have a dog, do you have pets too?cited by 820
- 2015Improving Neural Machine Translation Models with Monolingual Datacited by 784
- 2020Recipes for building an open-domain chatbotcited by 593
- 2021Towards Emotional Support Dialog Systemscited by 294
- 2016A Persona-Based Neural Conversation Modelcited by 221
- 2015A Neural Conversational Modelcited by 195
- 2019PullNet: Open Domain Question Answering with Iterative Retrieval on Knowledge Bases and Textcited by 182
- 2017Variational Reasoning for Question Answering with Knowledge Graphcited by 170
8 more
- 2017Emotional Chatting Machine: Emotional Conversation Generation with Internal and External Memorycited by 167
- 2018Open Domain Question Answering Using Early Fusion of Knowledge Bases and Textcited by 167
- 2019MoEL: Mixture of Empathetic Listenerscited by 91
- 2020PLATO-2: Towards Building an Open-Domain Chatbot via Curriculum Learningcited by 79
- 2019Personalized Dialogue Generation with Diversified Traitscited by 73
- 2017MojiTalk: Generating Emotional Responses at Scalecited by 64
- 2020Profile Consistency Identification for Open-domain Dialogue Agentscited by 22
- 2017Assigning personality/identity to a chatting machine for coherent conversation generationcited by 10
Built on by
Citing papers per year: 2022: 1.
1 paper.