LSTM based Conversation Models

Abstract

In this paper, we present a conversational model that incorporates both context and participant role for two-party conversations. Different architectures are explored for integrating participant role and context information into a Long Short-term Memory (LSTM) language model. The conversational model can function as a language model or a language generation model. Experiments on the Ubuntu Dialog Corpus show that our model can capture multiple turn interaction between participants. The proposed method outperforms a traditional LSTM model as measured by language model perplexity and response ranking. Generated responses show characteristic differences between the two participant roles.

References in corpus (5)

• A Neural Conversational Model
• A Persona-Based Neural Conversation Model
• deltaBLEU: A Discriminative Metric for Generation Tasks with Intrinsically Diverse Targets
• A Neural Network Approach to Context-Sensitive Generation of Conversational Responses
• Document Context Language Models

Cited by in corpus (19)

• Deep Reinforcement Learning for Dialogue Generation
• A Simple, Fast Diverse Decoding Algorithm for Neural Generation
• Adversarial Learning for Neural Dialogue Generation
• Conversational AI: The Science Behind the Alexa Prize
• Multi-Task Learning for Speaker-Role Adaptation in Neural Conversation Models
• Advancing the State of the Art in Open Domain Dialog Systems through the Alexa Prize
• Learning to Decode for Future Success
• A Survey of Natural Language Generation Techniques with a Focus on Dialogue Systems - Past, Present and Future Directions
• Neural Language Generation: Formulation, Methods, and Evaluation
• Hybrid Code Networks: practical and efficient end-to-end dialog control with supervised and reinforcement learning
• Scientific Information Extraction with Semi-supervised Neural Tagging
• The Rapidly Changing Landscape of Conversational Agents
• Self-Supervised Dialogue Learning
• Low-Rank RNN Adaptation for Context-Aware Language Modeling
• Information Extraction from Scientific Literature for Method Recommendation
• Retrieval-based Goal-Oriented Dialogue Generation
• Monolingual sentence matching for text simplification
• Incorporating Relevant Knowledge in Context Modeling and Response Generation
• Game-Based Video-Context Dialogue