A Neural Network Approach to Context-Sensitive Generation of Conversational Responses

Abstract

We present a novel response generation system that can be trained end to end on large quantities of unstructured Twitter conversations. A neural network architecture is used to address sparsity issues that arise when integrating contextual information into classic statistical models, allowing the system to take into account previous dialog utterances. Our dynamic-context generative models show consistent gains over both context-sensitive and non-context-sensitive Machine Translation and Information Retrieval baselines.

A. Sordoni, M. Galley, M. Auli, C. Brockett, Y. Ji, M. Mitchell, J.-Y. Nie, J. Gao, B. Dolan. 2015. A Neural Network Approach to Context-Sensitive Generation of Conversational Responses. In Proc. of NAACL-HLT. Pages 196-205

Cited by in corpus (27)

• A Simple, Fast Diverse Decoding Algorithm for Neural Generation
• Flexible End-to-End Dialogue System for Knowledge Grounded Conversation
• Best of Both Worlds: Transferring Knowledge from Discriminative Learning to a Generative Visual Dialog Model
• Context-aware Natural Language Generation with Recurrent Neural Networks
• Learning to Decode for Future Success
• Recent advances in conversational NLP : Towards the standardization of Chatbot building
• A Survey of Natural Language Generation Techniques with a Focus on Dialogue Systems - Past, Present and Future Directions
• Toward Continual Learning for Conversational Agents
• Are You Talking to Me? Reasoned Visual Dialog Generation through Adversarial Learning
• RubyStar: A Non-Task-Oriented Mixture Model Dialog System
• Shaping the Narrative Arc: An Information-Theoretic Approach to Collaborative Dialogue
• Generative Encoder-Decoder Models for Task-Oriented Spoken Dialog Systems with Chatting Capability
• Modeling Text-visual Mutual Dependency for Multi-modal Dialog Generation
• Neural Contextual Conversation Learning with Labeled Question-Answering Pairs
• Policy-Driven Neural Response Generation for Knowledge-Grounded Dialogue Systems
• Learning to Start for Sequence to Sequence Architecture
• End-to-end Adversarial Learning for Generative Conversational Agents
• RADDLE: An Evaluation Benchmark and Analysis Platform for Robust Task-oriented Dialog Systems
• A Sequential Matching Framework for Multi-turn Response Selection in Retrieval-based Chatbots
• Knowledge-incorporating ESIM models for Response Selection in Retrieval-based Dialog Systems
• OpenViDial 2.0: A Larger-Scale, Open-Domain Dialogue Generation Dataset with Visual Contexts
• Generating Challenge Datasets for Task-Oriented Conversational Agents through Self-Play
• Improving Computer Generated Dialog with Auxiliary Loss Functions and Custom Evaluation Metrics
• How Do Neural Sequence Models Generalize? Local and Global Context Cues for Out-of-Distribution Prediction
• Diversifying Topic-Coherent Response Generation for Natural Multi-turn Conversations
• Learning from Perturbations: Diverse and Informative Dialogue Generation with Inverse Adversarial Training
• AI-Powered Text Generation for Harmonious Human-Machine Interaction: Current State and Future Directions