Unsupervised Discrete Sentence Representation Learning for Interpretable Neural Dialog Generation

@inproceedings{Zhao2018UnsupervisedDS,
  title={Unsupervised Discrete Sentence Representation Learning for Interpretable Neural Dialog Generation},
  author={Tiancheng Zhao and Kyusong Lee and M. Esk{\'e}nazi},
  booktitle={ACL},
  year={2018}
}
The encoder-decoder dialog model is one of the most prominent methods used to build dialog systems in complex domains. [...] Key Method Building upon variational autoencoders (VAEs), we present two novel models, DI-VAE and DI-VST that improve VAEs and can discover interpretable semantics via either auto encoding or context predicting. Our methods have been validated on real-world dialog datasets to discover semantic representations and enhance encoder-decoder models with interpretable generation.Expand
89 Citations
Unsupervised Dialog Structure Learning
  • 20
  • PDF
An Efficient Policy Gradient Method for Conditional Dialogue Generation
  • L. Cai, Shuiwang Ji
  • Computer Science
  • 2019 IEEE International Conference on Data Mining (ICDM)
  • 2019
Generalizable and Explainable Dialogue Generation via Explicit Action Learning
  • Highly Influenced
  • PDF
Structured Attention for Unsupervised Dialogue Structure Induction
  • PDF
Discovering Dialog Structure Graph for Open-Domain Dialog Generation
  • PDF
Variational Auto-Encoder for text generation
Improving Neural Conversational Models with Entropy-Based Data Filtering
  • 18
  • PDF
PLATO: Pre-trained Dialogue Generation Model with Discrete Latent Variable
  • 23
  • PDF
Toward Interpretability of Dual-Encoder Models for Dialogue Response Suggestions
  • PDF
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 44 REFERENCES
A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues
  • 715
  • Highly Influential
  • PDF
Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders
  • 387
  • PDF
Toward Controlled Generation of Text
  • 542
  • Highly Influential
  • PDF
Generating Sentences from a Continuous Space
  • 1,320
  • Highly Influential
  • PDF
Latent Intention Dialogue Models
  • 109
  • PDF
Skip-Thought Vectors
  • 1,654
  • Highly Influential
  • PDF
Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
  • 11,140
  • PDF
Key-Value Retrieval Networks for Task-Oriented Dialogue
  • 197
  • PDF
Latent Variable Dialogue Models and their Diversity
  • 55
  • PDF
Neural Variational Inference for Text Processing
  • 364
  • PDF
...
1
2
3
4
5
...