Generative Encoder-Decoder Models for Task-Oriented Spoken Dialog Systems with Chatting Capability
arXiv:1706.08476
Abstract
Generative encoder-decoder models offer great promise in developing domain-general dialog systems. However, they have mainly been applied to open-domain conversations. This paper presents a practical and novel framework for building task-oriented dialog systems based on encoder-decoder models. This framework enables encoder-decoder models to accomplish slot-value independent decision-making and interact with external databases. Moreover, this paper shows the flexibility of the proposed method by interleaving chatting capability with a slot-filling system for better out-of-domain recovery. The models were trained on both real-user data from a bus information system and human-human chat data. Results show that the proposed framework achieves good performance in both offline evaluation metrics and in task success rate with human users.
Accepted as a long paper in SIGIDIAL 2017
References in corpus (16)
- Adam: A Method for Stochastic Optimization
- Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
- Recurrent Neural Network Regularization
- A Neural Conversational Model
- Convolutional Neural Networks for Sentence Classification
- Deep Reinforcement Learning for Dialogue Generation
- A Network-based End-to-End Trainable Task-oriented Dialogue System
- Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders
- Towards End-to-End Learning for Dialog State Tracking and Management using Deep Reinforcement Learning
- Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems
- End-to-end LSTM-based dialog control optimized with supervised and reinforcement learning
- Continuously Learning Neural Dialogue Management
- A Neural Network Approach to Context-Sensitive Generation of Conversational Responses
- Learning End-to-End Goal-Oriented Dialog
- Towards End-to-End Reinforcement Learning of Dialogue Agents for Information Access
- Reference-Aware Language Models