Generating Informative and Diverse Conversational Responses via Adversarial Information Maximization
Explore this paper's citation graph
Summary
Adversarial Information Maximization (AIM), an adversarial learning framework that addresses informativeness and diversity, and explicitly optimizes a variational lower bound on pairwise mutual information between query and response.
- Type
- article
- Published
- 2018-09-16
- Cited by
- 319
- References
- 47
- Access
- Open access
- OpenAlex
- https://openalex.org/W2890969459
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:52285447
Keywords
Adversarial system, Maximization, Leverage (statistics), Computer science, Pairwise comparison
References
- The IM algorithm: a variational approach to Information Maximization
- A Neural Network Approach to Context-Sensitive Generation of Conversational Responses
- A Neural Conversational Model
- Auto-Encoding Variational Bayes
- Bleu: a Method for Automatic Evaluation of Machine Translation
- Learning deep structured semantic models for web search using clickthrough data
- Vector-based Models of Semantic Composition
- ROUGE: A Package for Automatic Evaluation of Summaries
- Neural Responding Machine for Short-Text Conversation
- Deterministic Policy Gradient Algorithms
- A Comparison of Greedy and Optimal Assessment of Natural Language Student Input Using Word-to-Word Similarity Metrics
- Hierarchical Neural Network Generative Models for Movie Dialogues
- A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues
- Deep Reinforcement Learning for Dialogue Generation
- InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets
- SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient
- Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
- Adversarial Learning for Neural Dialogue Generation
- Improving Neural Machine Translation with Conditional Sequence Generative Adversarial Nets
- Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks
Cited by
- Multi-turn Dialogue Response Generation in an Adversarial Learning Framework
- Why Do Neural Response Generation Models Prefer Universal Replies?
- A bird's-eye view on coherence, and a worm's-eye view on cohesion
- Understanding Chat Messages for Sticker Recommendation in Hike Messenger
- Promoting Diversity for End-to-End Conversation Response Generation
- Jointly Optimizing Diversity and Relevance in Neural Response Generation
- Consistent Dialogue Generation with Self-supervised Feature Learning
- Knowledge-Grounded Response Generation with Deep Attentional Latent-Variable Model
- A Hybrid Retrieval-Generation Neural Conversation Model
- Improving Neural Conversational Models with Entropy-Based Data Filtering
- Jointly Learning Semantic Parser and Natural Language Generator via Dual Information Maximization
- Comparison of Diverse Decoding Methods from Conditional Language Models
- Improving Background Based Conversation with Context-aware Knowledge Pre-selection
- DAL: Dual Adversarial Learning for Dialogue Generation
- Neural Response Generation with Meta-words
- Reinforced Dynamic Reasoning for Conversational Question Generation
- Towards Generating Long and Coherent Text with Multi-Level Latent Variable Models
- Deep Chit-Chat: Deep Learning for Chatbots
- Investigating Evaluation of Open-Domain Dialogue Systems With Human Generated Multiple References
- Conversing by Reading: Contentful Neural Conversation with On-demand Machine Reading