PLATO: Pre-trained Dialogue Generation Model with Discrete Latent Variable

Siqi Bao, Huang He, Fan Wang, Hua Wu, Haifeng Wang


Abstract
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.
Anthology ID:
2020.acl-main.9
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2020
Address:
Online
Editors:
Dan Jurafsky, Joyce Chai, Natalie Schluter, Joel Tetreault
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
85–96
Language:
URL:
https://aclanthology.org/2020.acl-main.9
DOI:
10.18653/v1/2020.acl-main.9
Bibkey:
Cite (ACL):
Siqi Bao, Huang He, Fan Wang, Hua Wu, and Haifeng Wang. 2020. PLATO: Pre-trained Dialogue Generation Model with Discrete Latent Variable. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 85–96, Online. Association for Computational Linguistics.
Cite (Informal):
PLATO: Pre-trained Dialogue Generation Model with Discrete Latent Variable (Bao et al., ACL 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.acl-main.9.pdf
Video:
 http://slideslive.com/38928777
Code
 PaddlePaddle/Research +  additional community code
Data
DailyDialog