Emotional Chatting Machine: Emotional Conversation Generation with Internal and External Memory
arXiv:1704.01074
Abstract
Perception and expression of emotion are key factors to the success of dialogue systems or conversational agents. However, this problem has not been studied in large-scale conversation generation so far. In this paper, we propose Emotional Chatting Machine (ECM) that can generate appropriate responses not only in content (relevant and grammatical) but also in emotion (emotionally consistent). To the best of our knowledge, this is the first work that addresses the emotion factor in large-scale conversation generation. ECM addresses the factor using three new mechanisms that respectively (1) models the high-level abstraction of emotion expressions by embedding emotion categories, (2) captures the change of implicit internal emotion states, and (3) uses explicit emotion expressions with an external emotion vocabulary. Experiments show that the proposed model can generate responses appropriate not only in content but also in emotion.
Accepted in AAAI 2018
References in corpus (15)
- Sequence to Sequence Learning with Neural Networks
- Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
- TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
- Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
- How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation
- Deep Reinforcement Learning for Dialogue Generation
- Topic Aware Neural Response Generation
- A Simple, Fast Diverse Decoding Algorithm for Neural Generation
- Neural Responding Machine for Short-Text Conversation
- Toward Controlled Generation of Text
- Two are Better than One: An Ensemble of Retrieval- and Generation-Based Dialog Systems
- Sequence to Backward and Forward Sequences: A Content-Introducing Approach to Generative Short-Text Conversation
- Affect-LM: A Neural Language Model for Customizable Affective Text Generation
- Dialog state tracking, a machine reading approach using Memory Network
- Neural Contextual Conversation Learning with Labeled Question-Answering Pairs
Cited by in corpus (28)
- DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset
- Personalized Dialogue Generation with Diversified Traits
- Expression Analysis Based on Face Regions in Read-world Conditions
- Deep Learning for Sentiment Analysis : A Survey
- Zero-Resource Knowledge-Grounded Dialogue Generation
- NaturalConv: A Chinese Dialogue Dataset Towards Multi-turn Topic-driven Conversation
- Towards Explainable and Controllable Open Domain Dialogue Generation with Dialogue Acts
- Style Transfer in Text: Exploration and Evaluation
- An Adversarial Approach to High-Quality, Sentiment-Controlled Neural Dialogue Generation
- OpenViDial: A Large-Scale, Open-Domain Dialogue Dataset with Visual Contexts
- DialogXL: All-in-One XLNet for Multi-Party Conversation Emotion Recognition
- Utterance-level Dialogue Understanding: An Empirical Study
- Shaping the Narrative Arc: An Information-Theoretic Approach to Collaborative Dialogue
- DAL: Dual Adversarial Learning for Dialogue Generation
- Generating Emotionally Aligned Responses in Dialogues using Affect Control Theory
- End-to-end Adversarial Learning for Generative Conversational Agents
- The Rapidly Changing Landscape of Conversational Agents
- A Sequential Matching Framework for Multi-turn Response Selection in Retrieval-based Chatbots
- Discovering Dialog Structure Graph for Open-Domain Dialog Generation
- A Syntactically Constrained Bidirectional-Asynchronous Approach for Emotional Conversation Generation
- Knowledge-Grounded Dialogue Generation with Pre-trained Language Models
- OpenViDial 2.0: A Larger-Scale, Open-Domain Dialogue Generation Dataset with Visual Contexts
- Affective Neural Response Generation
- Investigation of Sentiment Controllable Chatbot
- StyleDGPT: Stylized Response Generation with Pre-trained Language Models
- DeepEmo: Learning and Enriching Pattern-Based Emotion Representations
- Improving Matching Models with Hierarchical Contextualized Representations for Multi-turn Response Selection
- Disambiguating Affective Stimulus Associations for Robot Perception and Dialogue