Explicit State Tracking with Semi-Supervisionfor Neural Dialogue Generation

  title={Explicit State Tracking with Semi-Supervisionfor Neural Dialogue Generation},
  author={Xisen Jin and Wenqiang Lei and Z. Ren and Hongshen Chen and Shangsong Liang and Y. Zhao and Dawei Yin},
  journal={Proceedings of the 27th ACM International Conference on Information and Knowledge Management},
  • Xisen Jin, Wenqiang Lei, +4 authors Dawei Yin
  • Published 2018
  • Computer Science
  • Proceedings of the 27th ACM International Conference on Information and Knowledge Management
The task of dialogue generation aims to automatically provide responses given previous utterances. Tracking dialogue states is an important ingredient in dialogue generation for estimating users' intention. However, the expensive nature of state labeling and the weak interpretability make the dialogue state tracking a challenging problem for both task-oriented and non-task-oriented dialogue generation: For generating responses in task-oriented dialogues, state tracking is usually learned from… Expand
Towards Low-Resource Semi-Supervised Dialogue Generation with Meta-Learning
Improving Limited Labeled Dialogue State Tracking with Self-Supervision
Semi-Supervised Variational Reasoning for Medical Dialogue Generation
Simulating User Satisfaction for the Evaluation of Task-oriented Dialogue Systems
Dialogue Systems in a Low-resource Scenario
  • 2020
Prediction, Selection, and Generation: Exploration of Knowledge-Driven Conversation System
Interactive Learning of Dialog Scenarios from Examples


Neural Belief Tracker: Data-Driven Dialogue State Tracking
Multiresolution Recurrent Neural Networks: An Application to Dialogue Response Generation
Chat More: Deepening and Widening the Chatting Topic via A Deep Model
Learning End-to-End Goal-Oriented Dialog
Incorporating Copying Mechanism in Sequence-to-Sequence Learning
Adam: A Method for Stochastic Optimization
Bleu: a Method for Automatic Evaluation of Machine Translation