Parallel Learning for Legal Intelligence: A HANOI Approach Based on Unified Prompting

doi:10.1109/TCSS.2023.3301400

CORC > 自动化研究所 > 中国科学院自动化研究所 > 多模态人工智能系统全国重点实验室

	Parallel Learning for Legal Intelligence: A HANOI Approach Based on Unified Prompting
	Song, Zhuoyang 1; Huang, Min 1; Miao, Qinghai 1; Wang, Fei-Yue 2
刊名	IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS
	2023-08-14
页码	11
关键词	Index Ternis- Natural language processing (NLP) parallel learning (PL) parallel systems pretrained language model (PLM) prompt tuning
ISSN号	2329-924X
DOI	10.1109/TCSS.2023.3301400
通讯作者	Miao, Qinghai(miaoqh@ucas.ac.cn)
英文摘要	Pretrained language models (PLMs) have made significant progress on various NLP tasks recently. However, PLMs encounter challenges when it comes to domain-specific tasks such as legal AI. These tasks often involve intricate expertise, expensive data annotation, and limited training data availability. To tackle this problem, we propose a human-oriented artificial-natural parallel system for organized intelligence (HANOI)-Legal based on the parallel learning (PL) framework. First, by regarding the description in PL as the pretraining process based on a large-scale corpus, we setup an artificial system based on a PLM. Second, to adapt the PLM to legal tasks with limited resources, we propose UniPrompt as a prescription. UniPrompt serves as a unified prompt-based training framework, enabling the utilization of diverse open datasets for these tasks. Third, we labeled a few task-specific legal data through distributed autonomous operations (DAO-II) for further fine-tuning. By combining a scalable unified-task-format reformulation and a unified-prompt-based training pipeline, HANOI-Legal leverages PLMs' linguistic capabilities acquired from a variety of open datasets to generate task-specific models. Our experiments in two legal domain tasks show that HANOI-Legal achieved an excellent performance in low-resource scenarios compared to the state-of-the-art prompt-based approach.
资助项目	National Key Research and Development Program of China[2020YFB2104001] ; National Natural Science Foundation of China[62271485] ; Open Project of the State Key Laboratory for Management and Control of Complex Systems[20220117]
WOS研究方向	Computer Science
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:001051270900001
资助机构	National Key Research and Development Program of China ; National Natural Science Foundation of China ; Open Project of the State Key Laboratory for Management and Control of Complex Systems
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/54017]
专题	多模态人工智能系统全国重点实验室
通讯作者	Miao, Qinghai
作者单位	1.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 2.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Song, Zhuoyang,Huang, Min,Miao, Qinghai,et al. Parallel Learning for Legal Intelligence: A HANOI Approach Based on Unified Prompting[J]. IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS,2023:11.
APA	Song, Zhuoyang,Huang, Min,Miao, Qinghai,&Wang, Fei-Yue.(2023).Parallel Learning for Legal Intelligence: A HANOI Approach Based on Unified Prompting.IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS,11.
MLA	Song, Zhuoyang,et al."Parallel Learning for Legal Intelligence: A HANOI Approach Based on Unified Prompting".IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS (2023):11.