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

2015/06/22 by Sordoni, Alessandro, Galley, Michel, Auli, Michael +6 · 2 citations
#Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Neural and Evolutionary Computing (cs.NE)

paper · doi:10.48550/arxiv.1506.06714

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.

Cited by

• \bfD³QE: Learning Discrete Distribution Discrepancy-aware Quantization Error for Autoregressive-Generated Image Detection
• A State-Update Prompting Strategy for Efficient and Robust Multi-turn Dialogue

Related

• Neural Responding Machine for Short-Text Conversation
• Exploring the context of recurrent neural network based conversational\n agents
• A Hybrid Retrieval-Generation Neural Conversation Model
• DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation
• Towards Coherent and Engaging Spoken Dialog Response Generation Using Automatic Conversation Evaluators