A Fine-grained Classification Method for Cross-domain Policy Texts Based on Instruction Tuning

IF 6.9 3区 管理学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS
Jingyun Sun, Xinlong Chen, Kaiyuan Zheng, Yan Zan
{"title":"A Fine-grained Classification Method for Cross-domain Policy Texts Based on Instruction Tuning","authors":"Jingyun Sun, Xinlong Chen, Kaiyuan Zheng, Yan Zan","doi":"10.1007/s10796-024-10554-2","DOIUrl":null,"url":null,"abstract":"<p>The well-organized structure of Policy Texts (PTs) is fundamental to intelligent governance, yet most PTs lack fine-grained category labels. PTs from different domains follow different classification systems, and traditional encoder-only models cannot directly handle scenarios where the label spaces of the source and target domains differ significantly, as their output layer typically is a fixed-dimensional classification head. Therefore, we propose a Cross-Domain Policy Text Classification (CDPTC) task. We introduce a method for the task called InstructCDPTC. This method, within an instruction tuning framework, transforms the classification task into a generation task, using the decoder-only model BigBird to predict masked tokens. We wrap the original PT within an instruction template containing a task description, a label description, and a mask sequence, which serve as input to BigBird. During training, we use the names of gold categories as the prediction targets for masked positions. During inference, we determine the final predicted category by computing the semantic distance between the averaged representations of the mask predictions and each candidate label. We constructed a dataset of 20,189 labeled policy texts from five different policy domains to evaluate InstructCDPTC. Experimental results demonstrate that InstructCDPTC achieves an F1 score of 0.824 under conditions where the sample distribution and label space of the target domain are entirely unseen, surpassing other baselines.</p>","PeriodicalId":13610,"journal":{"name":"Information Systems Frontiers","volume":"66 1","pages":""},"PeriodicalIF":6.9000,"publicationDate":"2024-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Information Systems Frontiers","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1007/s10796-024-10554-2","RegionNum":3,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, INFORMATION SYSTEMS","Score":null,"Total":0}
引用次数: 0

Abstract

The well-organized structure of Policy Texts (PTs) is fundamental to intelligent governance, yet most PTs lack fine-grained category labels. PTs from different domains follow different classification systems, and traditional encoder-only models cannot directly handle scenarios where the label spaces of the source and target domains differ significantly, as their output layer typically is a fixed-dimensional classification head. Therefore, we propose a Cross-Domain Policy Text Classification (CDPTC) task. We introduce a method for the task called InstructCDPTC. This method, within an instruction tuning framework, transforms the classification task into a generation task, using the decoder-only model BigBird to predict masked tokens. We wrap the original PT within an instruction template containing a task description, a label description, and a mask sequence, which serve as input to BigBird. During training, we use the names of gold categories as the prediction targets for masked positions. During inference, we determine the final predicted category by computing the semantic distance between the averaged representations of the mask predictions and each candidate label. We constructed a dataset of 20,189 labeled policy texts from five different policy domains to evaluate InstructCDPTC. Experimental results demonstrate that InstructCDPTC achieves an F1 score of 0.824 under conditions where the sample distribution and label space of the target domain are entirely unseen, surpassing other baselines.

基于指令调整的跨域政策文本细粒度分类方法
条理清晰的政策文本(PTs)结构是智能治理的基础,但大多数政策文本缺乏细粒度的类别标签。不同领域的政策文本遵循不同的分类体系,而传统的纯编码器模型无法直接处理源领域和目标领域标签空间差异较大的情况,因为其输出层通常是一个固定维度的分类头。因此,我们提出了跨域策略文本分类(CDPTC)任务。我们为该任务引入了一种名为 InstructCDPTC 的方法。该方法在指令调整框架内将分类任务转化为生成任务,使用纯解码器模型 BigBird 来预测掩码标记。我们将原始 PT 包裹在一个指令模板中,其中包含任务描述、标签描述和掩码序列,作为 BigBird 的输入。在训练过程中,我们使用黄金类别的名称作为屏蔽位置的预测目标。在推理过程中,我们通过计算掩码预测的平均表示与每个候选标签之间的语义距离来确定最终预测的类别。我们构建了一个由 20,189 篇来自五个不同政策领域的标注政策文本组成的数据集来评估 InstructCDPTC。实验结果表明,在目标领域的样本分布和标签空间完全不可见的条件下,InstructCDPTC 的 F1 得分为 0.824,超过了其他基线。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Information Systems Frontiers
Information Systems Frontiers 工程技术-计算机:理论方法
CiteScore
13.30
自引率
18.60%
发文量
127
审稿时长
9 months
期刊介绍: The interdisciplinary interfaces of Information Systems (IS) are fast emerging as defining areas of research and development in IS. These developments are largely due to the transformation of Information Technology (IT) towards networked worlds and its effects on global communications and economies. While these developments are shaping the way information is used in all forms of human enterprise, they are also setting the tone and pace of information systems of the future. The major advances in IT such as client/server systems, the Internet and the desktop/multimedia computing revolution, for example, have led to numerous important vistas of research and development with considerable practical impact and academic significance. While the industry seeks to develop high performance IS/IT solutions to a variety of contemporary information support needs, academia looks to extend the reach of IS technology into new application domains. Information Systems Frontiers (ISF) aims to provide a common forum of dissemination of frontline industrial developments of substantial academic value and pioneering academic research of significant practical impact.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信