Unsupervised Dialog Structure Learning

@inproceedings{Shi2019UnsupervisedDS,
  title={Unsupervised Dialog Structure Learning},
  author={Weiyan Shi and Tiancheng Zhao and Zhou Yu},
  booktitle={NAACL-HLT},
  year={2019}
}
Learning a shared dialog structure from a set of task-oriented dialogs is an important challenge in computational linguistics. The learned dialog structure can shed light on how to analyze human dialogs, and more importantly contribute to the design and evaluation of dialog systems. We propose to extract dialog structures using a modified VRNN model with discrete latent vectors. Different from existing HMM-based models, our model is based on variational-autoencoder (VAE). Such model is able to… Expand
20 Citations
Structured Attention for Unsupervised Dialogue Structure Induction
  • PDF
Discovering Dialog Structure Graph for Open-Domain Dialog Generation
  • Highly Influenced
  • PDF
Variational Autoencoding Dialogue Sub-Structures Using a Novel Hierarchical Annotation Schema
Recent Advances and Challenges in Task-oriented Dialog System
  • 6
  • PDF
Improving Limited Labeled Dialogue State Tracking with Self-Supervision
  • PDF
Dialogue Systems in a Low-resource Scenario
  • 2020
  • Highly Influenced
  • PDF
Data-Efficient Goal-Oriented Conversation with Dialogue Knowledge Transfer Networks
  • 4
  • PDF
...
1
2
...

References

SHOWING 1-10 OF 29 REFERENCES
Zero-Shot Dialog Generation with Cross-Domain Latent Actions
  • 43
  • PDF
Discovering Latent Structure in Task-Oriented Dialogues
  • 38
  • PDF
A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues
  • 715
  • PDF
Learning the Structure of Task-Oriented Conversations from the Corpus of In-Domain Dialogs
  • 20
  • PDF
Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders
  • 387
  • PDF
Sentiment Adaptive End-to-End Dialog Systems
  • 34
  • PDF
A Network-based End-to-End Trainable Task-oriented Dialogue System
  • 645
  • PDF
...
1
2
3
...