Abstract
While recent neural encoder-decoder models have shown great promise in modeling open-domain conversations, they often generate dull and generic responses. Unlike past work that has focused on diversifying the output of the decoder from word-level to alleviate this problem, we present a novel framework based on conditional variational autoencoders that capture the discourse-level diversity in the encoder. Our model uses latent variables to learn a distribution over potential conversational intents and generates diverse responses using only greedy decoders. We have further developed a novel variant that is integrated with linguistic prior knowledge for better performance. Finally, the training procedure is improved through introducing a bag-of-word loss. Our proposed models have been validated to generate significantly more diverse responses than baseline approaches and exhibit competence of discourse-level decision-making.- Anthology ID:
- P17-1061
- Volume:
- Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- July
- Year:
- 2017
- Address:
- Vancouver, Canada
- Editors:
- Regina Barzilay, Min-Yen Kan
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 654–664
- Language:
- URL:
- https://aclanthology.org/P17-1061
- DOI:
- 10.18653/v1/P17-1061
- Cite (ACL):
- Tiancheng Zhao, Ran Zhao, and Maxine Eskenazi. 2017. Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 654–664, Vancouver, Canada. Association for Computational Linguistics.
- Cite (Informal):
- Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders (Zhao et al., ACL 2017)
- PDF:
- https://preview.aclanthology.org/proper-vol2-ingestion/P17-1061.pdf
- Code
- snakeztc/NeuralDialog-CVAE
- Data
- DailyDialog, Switchboard-1 Corpus