Abstract
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 capture more dynamics in dialogs beyond the surface forms of the language. We find that qualitatively, our method extracts meaningful dialog structure, and quantitatively, outperforms previous models on the ability to predict unseen data. We further evaluate the model’s effectiveness in a downstream task, the dialog system building task. Experiments show that, by integrating the learned dialog structure into the reward function design, the model converges faster and to a better outcome in a reinforcement learning setting.- Anthology ID:
- N19-1178
- Volume:
- Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
- Month:
- June
- Year:
- 2019
- Address:
- Minneapolis, Minnesota
- Venue:
- NAACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1797–1807
- Language:
- URL:
- https://aclanthology.org/N19-1178
- DOI:
- 10.18653/v1/N19-1178
- Cite (ACL):
- Weiyan Shi, Tiancheng Zhao, and Zhou Yu. 2019. Unsupervised Dialog Structure Learning. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 1797–1807, Minneapolis, Minnesota. Association for Computational Linguistics.
- Cite (Informal):
- Unsupervised Dialog Structure Learning (Shi et al., NAACL 2019)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/N19-1178.pdf
- Code
- wyshi/Unsupervised-Structure-Learning