XDAI: A Tuning-free Framework for Exploiting Pre-trained Language Models in Knowledge Grounded Dialogue Generation

被引:7
作者
Yu, Jifan [1 ]
Zhang, Xiaohan [1 ,2 ]
Xu, Yifan [1 ]
Lei, Xuanyu [1 ]
Guan, Xinyu [3 ]
Zhang, Jing [4 ]
Hou, Lei [5 ,6 ]
Li, Juanzi [5 ,6 ]
Tang, Jie [5 ,6 ]
机构
[1] Tsinghua Univ, Beijing, Peoples R China
[2] Zhipu AI, Beijing, Peoples R China
[3] Biendata, Beijing, Peoples R China
[4] Renmin Univ China, Sch Informat, Beijing, Peoples R China
[5] Tsinghua Univ, BNRist, Dept Comp Sci & Technol, Beijing, Peoples R China
[6] Tsinghua Univ, Inst Artificial Intelligence, KIRC, Beijing, Peoples R China
来源
PROCEEDINGS OF THE 28TH ACM SIGKDD CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING, KDD 2022 | 2022年
关键词
Pre-trained Model Exploitation; Dialogue System;
D O I
10.1145/3534678.3539135
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Large-scale pre-trained language models (PLMs) have shown promising advances on various downstream tasks, among which dialogue is one of the most concerned. However, there remain challenges for individual developers to create a knowledge-grounded dialogue system upon such big models because of the expensive cost of collecting the knowledge resources for supporting the system as well as tuning these large models for the task. To tackle these obstacles, we propose XDAI, a knowledge-grounded dialogue system that is equipped with the prompt-aware tuning-free PLM exploitation and supported by the ready-to-use open-domain external knowledge resources plus the easy-to-change domain-specific mechanism. With XDAI, the developers can leverage the PLMs without any fine-tuning cost to quickly create the open-domain dialogue systems as well as easily customize their own domain-specific systems. Extensive experiments including human evaluation, Turing test, and online evaluation have demonstrated the competitive performance of XDAI compared with the state-of-the-art general PLMs and specific PLMs for dialogue. XDAI pilots studies on the exploitation of PLMs and made intriguing findings which could be inspiring for the future research on other PLM-based applications. Developers and related researchers can get access to our repository at https://github.com/THUDM/XDAI, which presents a series of APIs, incremental toolkits and chatbot service of XDAI platform.
引用
收藏
页码:4422 / 4432
页数:11
相关论文
empty
未找到相关数据