Sentiment Adaptive End-to-End Dialog Systems

Abstract

End-to-end learning framework is useful for building dialog systems for its simplicity in training and efficiency in model updating. However, current end-to-end approaches only consider user semantic inputs in learning and under-utilize other user information. Therefore, we propose to include user sentiment obtained through multimodal information (acoustic, dialogic and textual), in the end-to-end learning framework to make systems more user-adaptive and effective. We incorporated user sentiment information in both supervised and reinforcement learning settings. In both settings, adding sentiment information reduced the dialog length and improved the task success rate on a bus information search task. This work is the first attempt to incorporate multimodal user information in the adaptive end-to-end dialog system training framework and attained state-of-the-art performance.

ACL 2018

References in corpus (9)

• ADADELTA: An Adaptive Learning Rate Method
• Optimizing Dialogue Management with Reinforcement Learning: Experiments with the NJFun System
• A Network-based End-to-End Trainable Task-oriented Dialogue System
• A User Simulator for Task-Completion Dialogues
• Towards End-to-End Learning for Dialog State Tracking and Management using Deep Reinforcement Learning
• An End-to-End Trainable Neural Network Model with Belief Tracking for Task-Oriented Dialog
• Query-Reduction Networks for Question Answering
• Learning End-to-End Goal-Oriented Dialog
• Iterative Policy Learning in End-to-End Trainable Task-Oriented Neural Dialog Models

Cited by in corpus (5)

• Effects of Persuasive Dialogues: Testing Bot Identities and Inquiry Strategies
• Unsupervised Dialog Structure Learning
• Fine-Grained Sentence Functions for Short-Text Conversation
• How to Build User Simulators to Train RL-based Dialog Systems
• Variational Reward Estimator Bottleneck: Learning Robust Reward Estimator for Multi-Domain Task-Oriented Dialog