Investigation of Language Understanding Impact for Reinforcement Learning Based Dialogue Systems
arXiv:1703.07055
Abstract
Language understanding is a key component in a spoken dialogue system. In this paper, we investigate how the language understanding module influences the dialogue system performance by conducting a series of systematic experiments on a task-oriented neural dialogue system in a reinforcement learning based setting. The empirical study shows that among different types of language understanding errors, slot-level errors can have more impact on the overall performance of a dialogue system compared to intent-level errors. In addition, our experiments demonstrate that the reinforcement learning based dialogue system is able to learn when and what to confirm in order to achieve better performance and greater robustness.
arXiv comment5 pages, 5 figures
References in corpus (6)
- Deep Reinforcement Learning for Dialogue Generation
- A User Simulator for Task-Completion Dialogues
- Towards End-to-End Learning for Dialog State Tracking and Management using Deep Reinforcement Learning
- End-to-end LSTM-based dialog control optimized with supervised and reinforcement learning
- Continuously Learning Neural Dialogue Management
- End-to-End Joint Learning of Natural Language Understanding and Dialogue Manager
Cited by in corpus (7)
- Why We Need New Evaluation Metrics for NLG
- Composite Task-Completion Dialogue Policy Learning via Hierarchical Deep Reinforcement Learning
- Investigation of Error Simulation Techniques for Learning Dialog Policies for Conversational Error Recovery
- Deep Active Learning for Dialogue Generation
- Conversational Recommender System
- Towards a Universal NLG for Dialogue Systems and Simulators with Future Bridging
- Interactive Storytelling for Children: A Case-study of Design and Development Considerations for Ethical Conversational AI