CSpace  > 中国科学院计算技术研究所期刊论文  > 英文
NIR-Prompt: A Multi-task Generalized Neural Information Retrieval Training Framework
Xu, Shicheng1,2; Pang, Liang1; Shen, Huawei1,2; Cheng, Xueqi2,3
2024-03-01
发表期刊ACM TRANSACTIONS ON INFORMATION SYSTEMS
ISSN1046-8188
卷号42期号:2页码:32
摘要Information retrieval aims to find information that meets users' needs from the corpus. Different needs correspond to different IR tasks such as document retrieval, open-domain question answering, retrieval-based dialogue, and so on, while they share the same schema to estimate the relationship between texts. It indicates that a good IR model can generalize to different tasks and domains. However, previous studies indicate that state-of-the-art neural information retrieval (NIR) models, e.g., pre-trained language models (PLMs) are hard to generalize. It is mainly because the end-to-end fine-tuning paradigm makes the model overemphasize task-specific signals and domain biases but loses the ability to capture generalized essential signals. To address this problem, we propose a novel NIR training framework named NIR-Prompt for retrieval and reranking stages based on the idea of decoupling signal capturing and combination. NIR-Prompt exploits Essential Matching Module (EMM) to capture the essential matching signals and gets the description of tasks by Matching Description Module (MDM). The description is used as task-adaptation information to combine the essential matching signals to adapt to different tasks. Experiments under in-domain multi-task, out-of-domain multi-task, and new task adaptation settings show that NIR-Prompt can improve the generalization of PLMs in NIR for both retrieval and reranking stages compared with baselines.
关键词Neural information retrieval dense retrieval reranking prompt learning
DOI10.1145/3626092
收录类别SCI
语种英语
资助项目National Key R&D Program of China[2022YFB3103700] ; National Key R&D Program of China[2022YFB3103704] ; National Natural Science Foundation of China (NSFC)[62276248] ; Youth Innovation Promotion Association CAS[2023111]
WOS研究方向Computer Science
WOS类目Computer Science, Information Systems
WOS记录号WOS:001152702600025
出版者ASSOC COMPUTING MACHINERY
引用统计
被引频次:1[WOS]   [WOS记录]     [WOS相关记录]
文献类型期刊论文
条目标识符http://119.78.100.204/handle/2XEOYT63/38368
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Pang, Liang
作者单位1.Chinese Acad Sci, Inst Comp Technol, Data Intelligence Syst Res Ctr, Beijing, Peoples R China
2.Univ Chinese Acad Sci, Beijing, Peoples R China
3.Chinese Acad Sci, Inst Comp Technol, CAS Key Lab Network Data Sci & Technol, Beijing, Peoples R China
推荐引用方式
GB/T 7714
Xu, Shicheng,Pang, Liang,Shen, Huawei,et al. NIR-Prompt: A Multi-task Generalized Neural Information Retrieval Training Framework[J]. ACM TRANSACTIONS ON INFORMATION SYSTEMS,2024,42(2):32.
APA Xu, Shicheng,Pang, Liang,Shen, Huawei,&Cheng, Xueqi.(2024).NIR-Prompt: A Multi-task Generalized Neural Information Retrieval Training Framework.ACM TRANSACTIONS ON INFORMATION SYSTEMS,42(2),32.
MLA Xu, Shicheng,et al."NIR-Prompt: A Multi-task Generalized Neural Information Retrieval Training Framework".ACM TRANSACTIONS ON INFORMATION SYSTEMS 42.2(2024):32.
条目包含的文件
条目无相关文件。
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Xu, Shicheng]的文章
[Pang, Liang]的文章
[Shen, Huawei]的文章
百度学术
百度学术中相似的文章
[Xu, Shicheng]的文章
[Pang, Liang]的文章
[Shen, Huawei]的文章
必应学术
必应学术中相似的文章
[Xu, Shicheng]的文章
[Pang, Liang]的文章
[Shen, Huawei]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。