EVA2.0: Investigating Open-domain Chinese Dialogue Systems with Large-scale Pre-training

doi:10.1007/s11633-022-1387-3

CASIA OpenIR > 学术期刊 > Machine Intelligence Research

	EVA2.0: Investigating Open-domain Chinese Dialogue Systems with Large-scale Pre-training
	Yuxian Gu 1,2; Jiaxin Wen 1,2; Hao Sun 1,2; Yi Song 1,2; Pei Ke 1,2; Chujie Zheng 1,2; Zheng Zhang1,2 ; Jianzhu Yao 2; Lei Liu 3; Xiaoyan Zhu 1,2; Minlie Huang 1,2
发表期刊	Machine Intelligence Research
ISSN	2731-538X
	2023
卷号	20 期号:2 页码:207-219
摘要	Large-scale pre-training has shown remarkable performance in building open-domain dialogue systems. However, previous works mainly focus on showing and evaluating the conversational performance of the released dialogue model, ignoring the discussion of some key factors towards a powerful human-like chatbot, especially in Chinese scenarios. In this paper, we conduct extensive experiments to investigate these under-explored factors, including data quality control, model architecture designs, training approaches, and decoding strategies. We propose EVA2.0, a large-scale pre-trained open-domain Chinese dialogue model with 2.8 billion parameters, and will make our models and codes publicly available. Automatic and human evaluations show that EVA2.0 significantly outperforms other open-source counterparts. We also discuss the limitations of this work by presenting some failure cases and pose some future research directions on large-scale Chinese open-domain dialogue systems.
关键词	Natural language processing deep learning (DL) large-scale pre-training dialogue systems Chinese open-domain conversational model
DOI	10.1007/s11633-022-1387-3
引用统计	被引频次：3[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/55975
专题	学术期刊_Machine Intelligence Research
作者单位	1.The Conversational AI Group, Tsinghua University, Beijing 100084, China 2.Department of Computer Science and Technology, Tsinghua University, Beijing 100084, China 3.Department of Electrical Engineering and Computer Science, York University, Toronto M3J1P3, Canada
推荐引用方式 GB/T 7714	Yuxian Gu,Jiaxin Wen,Hao Sun,et al. EVA2.0: Investigating Open-domain Chinese Dialogue Systems with Large-scale Pre-training[J]. Machine Intelligence Research,2023,20(2):207-219.
APA	Yuxian Gu.,Jiaxin Wen.,Hao Sun.,Yi Song.,Pei Ke.,...&Minlie Huang.(2023).EVA2.0: Investigating Open-domain Chinese Dialogue Systems with Large-scale Pre-training.Machine Intelligence Research,20(2),207-219.
MLA	Yuxian Gu,et al."EVA2.0: Investigating Open-domain Chinese Dialogue Systems with Large-scale Pre-training".Machine Intelligence Research 20.2(2023):207-219.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
MIR-2022-09-289.pdf（1846KB）	期刊论文	出版稿	开放获取	CC BY-NC-SA	浏览下载