End-to-end latent-variable task-oriented dialogue system with exact log-likelihood optimization

• Main Authors: Xu, H., Peng, Haiyun, Xie, H., Cambria, Erik, Zhou, L., Zheng, W.
• Other Authors: School of Computer Science and Engineering
• Format: Article
• Language: English
• Published: 2021
• Subjects: Engineering::Computer science and engineering; Dialogue Model; Hierarchical Encoder-Decoder
• Online Access: https://hdl.handle.net/10356/154469
• Institution: Nanyang Technological University

We propose an end-to-end dialogue model based on a hierarchical encoder-decoder, which employed a discrete latent variable to learn underlying dialogue intentions. The system is able to model the structure of utterances dominated by statistics of the language and the dependencies among utterances in...