Unsupervised Discrete Sentence Representation Learning for Interpretable Neural Dialog Generation

Tiancheng Zhao, Kyusong Lee, Maxine Eskenazi


Abstract
The encoder-decoder dialog model is one of the most prominent methods used to build dialog systems in complex domains. Yet it is limited because it cannot output interpretable actions as in traditional systems, which hinders humans from understanding its generation process. We present an unsupervised discrete sentence representation learning method that can integrate with any existing encoder-decoder dialog models for interpretable response generation. 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.
Anthology ID:
P18-1101
Volume:
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2018
Address:
Melbourne, Australia
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1098–1107
Language:
URL:
https://aclanthology.org/P18-1101
DOI:
10.18653/v1/P18-1101
Bibkey:
Cite (ACL):
Tiancheng Zhao, Kyusong Lee, and Maxine Eskenazi. 2018. Unsupervised Discrete Sentence Representation Learning for Interpretable Neural Dialog Generation. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1098–1107, Melbourne, Australia. Association for Computational Linguistics.
Cite (Informal):
Unsupervised Discrete Sentence Representation Learning for Interpretable Neural Dialog Generation (Zhao et al., ACL 2018)
Copy Citation:
PDF:
https://preview.aclanthology.org/paclic-22-ingestion/P18-1101.pdf
Note:
 P18-1101.Notes.pdf
Presentation:
 P18-1101.Presentation.pdf
Video:
 https://vimeo.com/285802293
Code
 snakeztc/NeuralDialog-LAED +  additional community code
Data
Penn Treebank