EmpTransfo: A Multi-head Transformer Architecture for Creating Empathetic Dialog Systems
arXiv:2003.02958
Abstract
Understanding emotions and responding accordingly is one of the biggest challenges of dialog systems. This paper presents EmpTransfo, a multi-head Transformer architecture for creating an empathetic dialog system. EmpTransfo utilizes state-of-the-art pre-trained models (e.g., OpenAI-GPT) for language generation, though models with different sizes can be used. We show that utilizing the history of emotions and other metadata can improve the quality of generated conversations by the dialog system. Our experimental results using a challenging language corpus show that the proposed approach outperforms other models in terms of Hit@1 and PPL (Perplexity).
References in corpus (10)
- HuggingFace's Transformers: State-of-the-art Natural Language Processing
- The Curious Case of Neural Text Degeneration
- DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset
- Facial Expression Recognition Using Enhanced Deep 3D Convolutional Neural Networks
- TransferTransfo: A Transfer Learning Approach for Neural Network Based Conversational Agents
- Personalizing Dialogue Agents: I have a dog, do you have pets too?
- A Neural Network Approach to Context-Sensitive Generation of Conversational Responses
- MojiTalk: Generating Emotional Responses at Scale
- Affect-Driven Dialog Generation
- BLEU is Not Suitable for the Evaluation of Text Simplification
Cited by in corpus (8)
- Empathetic Conversational Systems: A Review of Current Advances, Gaps, and Opportunities
- Emotion-Aware Transformer Encoder for Empathetic Dialogue Generation
- Towards Persona-Based Empathetic Conversational Models
- CoMAE: A Multi-factor Hierarchical Framework for Empathetic Response Generation
- Towards Emotional Support Dialog Systems
- Multi-Task Learning of Generation and Classification for Emotion-Aware Dialogue Response Generation
- CloneBot: Personalized Dialogue-Response Predictions
- Automatically Select Emotion for Response via Personality-affected Emotion Transition