PLATO: Pre-trained Dialogue Generation Model with Discrete Latent Variable
Siqi Bao, He Huang, Fan Wang, Hua Ren Wu, Haifeng Wang · 2020
Pre-training models have been proved effective for a wide range of natural language processing tasks.Inspired by this, we propose a novel dialogue generation pre-training framework to support various kinds of conversations, including chit-chat, knowledge grounded dialogues, and conversational question answering.In this framework, we adopt flexible attention mechanisms to fully leverage the bi-directional context and the uni-directional characteristic of language generation.We also introduce discrete latent variables to tackle the inherent one-to-many mapping problem in response generation.Two reciprocal tasks of response generation and latent act recognition are designed and carried out simultaneously within a shared network.Comprehensive experiments on three publicly available datasets verify the effectiveness and superiority of the proposed framework.