Pretrained Language Models for Dialogue Generation with Multiple Input Sources

2020/10/15 by Yu Cao, Cao, Yu, Wei Bi +5
Computer Science · #Natural Language Processing Techniques #Speech and dialogue systems #Topic Modeling #cs.CL

paper · pdf · doi:10.48550/arxiv.2010.07576

9 pages (containing 4 pages of references and appendix), accepted to EMNLP2020-Findings

arxiv created 2020/10/15 · arxiv updated 2020/10/16

Abstract

Large-scale pretrained language models have achieved outstanding performance on natural language understanding tasks. However, it is still under investigating how to apply them to dialogue generation tasks, especially those with responses conditioned on multiple sources. Previous work simply concatenates all input sources or averages information from different input sources. In this work, we study dialogue models with multiple input sources adapted from the pretrained language model GPT2. We explore various methods to fuse multiple separate attention information corresponding to different sources. Our experimental results show that proper fusion methods deliver higher relevance with dialogue history than simple fusion baselines.

Related

• PLATO: Pre-trained Dialogue Generation Model with Discrete Latent Variable
• Knowledge-Grounded Dialogue Generation with Pre-trained Language Models
• Hello, It's GPT-2 -- How Can I Help You? Towards the Use of Pretrained Language Models for Task-Oriented Dialogue Systems
• Open-Domain Dialogue Generation Based on Pre-trained Language Models
• Multi-Referenced Training for Dialogue Response Generation