需求分类的零射击学习:探索性研究

Waad Alhoshan, Alessio Ferrari, Liping Zhao
{"title":"需求分类的零射击学习:探索性研究","authors":"Waad Alhoshan, Alessio Ferrari, Liping Zhao","doi":"10.48550/arXiv.2302.04723","DOIUrl":null,"url":null,"abstract":"Context: Requirements engineering researchers have been experimenting with machine learning and deep learning approaches for a range of RE tasks, such as requirements classification, requirements tracing, ambiguity detection, and modelling. However, most of today's ML/DL approaches are based on supervised learning techniques, meaning that they need to be trained using a large amount of task-specific labelled training data. This constraint poses an enormous challenge to RE researchers, as the lack of labelled data makes it difficult for them to fully exploit the benefit of advanced ML/DL technologies. Objective: This paper addresses this problem by showing how a zero-shot learning approach can be used for requirements classification without using any labelled training data. We focus on the classification task because many RE tasks can be framed as classification problems. Method: The ZSL approach used in our study employs contextual word-embeddings and transformer-based language models. We demonstrate this approach through a series of experiments to perform three classification tasks: (1)FR/NFR: classification functional requirements vs non-functional requirements; (2)NFR: identification of NFR classes; (3)Security: classification of security vs non-security requirements. Results: The study shows that the ZSL approach achieves an F1 score of 0.66 for the FR/NFR task. For the NFR task, the approach yields F1~0.72-0.80, considering the most frequent classes. For the Security task, F1~0.66. All of the aforementioned F1 scores are achieved with zero-training efforts. Conclusion: This study demonstrates the potential of ZSL for requirements classification. An important implication is that it is possible to have very little or no training data to perform classification tasks. The proposed approach thus contributes to the solution of the long-standing problem of data shortage in RE.","PeriodicalId":133352,"journal":{"name":"Inf. Softw. Technol.","volume":"60 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-02-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"9","resultStr":"{\"title\":\"Zero-Shot Learning for Requirements Classification: An Exploratory Study\",\"authors\":\"Waad Alhoshan, Alessio Ferrari, Liping Zhao\",\"doi\":\"10.48550/arXiv.2302.04723\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Context: Requirements engineering researchers have been experimenting with machine learning and deep learning approaches for a range of RE tasks, such as requirements classification, requirements tracing, ambiguity detection, and modelling. However, most of today's ML/DL approaches are based on supervised learning techniques, meaning that they need to be trained using a large amount of task-specific labelled training data. This constraint poses an enormous challenge to RE researchers, as the lack of labelled data makes it difficult for them to fully exploit the benefit of advanced ML/DL technologies. Objective: This paper addresses this problem by showing how a zero-shot learning approach can be used for requirements classification without using any labelled training data. We focus on the classification task because many RE tasks can be framed as classification problems. Method: The ZSL approach used in our study employs contextual word-embeddings and transformer-based language models. We demonstrate this approach through a series of experiments to perform three classification tasks: (1)FR/NFR: classification functional requirements vs non-functional requirements; (2)NFR: identification of NFR classes; (3)Security: classification of security vs non-security requirements. Results: The study shows that the ZSL approach achieves an F1 score of 0.66 for the FR/NFR task. For the NFR task, the approach yields F1~0.72-0.80, considering the most frequent classes. For the Security task, F1~0.66. All of the aforementioned F1 scores are achieved with zero-training efforts. Conclusion: This study demonstrates the potential of ZSL for requirements classification. An important implication is that it is possible to have very little or no training data to perform classification tasks. The proposed approach thus contributes to the solution of the long-standing problem of data shortage in RE.\",\"PeriodicalId\":133352,\"journal\":{\"name\":\"Inf. Softw. Technol.\",\"volume\":\"60 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-02-09\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"9\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Inf. Softw. Technol.\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.48550/arXiv.2302.04723\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Inf. Softw. Technol.","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.48550/arXiv.2302.04723","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 9

摘要

背景:需求工程研究人员一直在试验机器学习和深度学习方法来完成一系列可重构任务,例如需求分类、需求跟踪、模糊检测和建模。然而,今天的大多数ML/DL方法都是基于监督学习技术,这意味着它们需要使用大量特定任务的标记训练数据进行训练。这一限制给可再生能源研究人员带来了巨大的挑战,因为缺乏标记数据使他们难以充分利用先进的ML/DL技术的优势。目的:本文通过展示如何在不使用任何标记训练数据的情况下使用零射击学习方法来解决这个问题。我们将重点放在分类任务上,因为许多可重构任务可以被定义为分类问题。方法:在我们的研究中使用的ZSL方法采用上下文词嵌入和基于转换的语言模型。我们通过一系列实验来演示这种方法,以执行三个分类任务:(1)FR/NFR:分类功能需求与非功能需求;(2)NFR: NFR类别的鉴定;(3)安全性:安全性与非安全性需求的分类。结果:研究表明ZSL方法对FR/NFR任务的F1得分为0.66。对于NFR任务,考虑到最频繁的类,该方法的结果为F1~0.72-0.80。对于Security任务,F1~0.66。上述所有F1成绩都是在零训练的情况下取得的。结论:本研究证明了ZSL在需求分类方面的潜力。一个重要的含义是,有可能只有很少或没有训练数据来执行分类任务。因此,该方法有助于解决长期存在的可重构数据短缺问题。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Zero-Shot Learning for Requirements Classification: An Exploratory Study
Context: Requirements engineering researchers have been experimenting with machine learning and deep learning approaches for a range of RE tasks, such as requirements classification, requirements tracing, ambiguity detection, and modelling. However, most of today's ML/DL approaches are based on supervised learning techniques, meaning that they need to be trained using a large amount of task-specific labelled training data. This constraint poses an enormous challenge to RE researchers, as the lack of labelled data makes it difficult for them to fully exploit the benefit of advanced ML/DL technologies. Objective: This paper addresses this problem by showing how a zero-shot learning approach can be used for requirements classification without using any labelled training data. We focus on the classification task because many RE tasks can be framed as classification problems. Method: The ZSL approach used in our study employs contextual word-embeddings and transformer-based language models. We demonstrate this approach through a series of experiments to perform three classification tasks: (1)FR/NFR: classification functional requirements vs non-functional requirements; (2)NFR: identification of NFR classes; (3)Security: classification of security vs non-security requirements. Results: The study shows that the ZSL approach achieves an F1 score of 0.66 for the FR/NFR task. For the NFR task, the approach yields F1~0.72-0.80, considering the most frequent classes. For the Security task, F1~0.66. All of the aforementioned F1 scores are achieved with zero-training efforts. Conclusion: This study demonstrates the potential of ZSL for requirements classification. An important implication is that it is possible to have very little or no training data to perform classification tasks. The proposed approach thus contributes to the solution of the long-standing problem of data shortage in RE.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Robustness assessment of hyperspectral image CNNs using metamorphic testing Towards accurate recommendations of merge conflicts resolution strategies Characteristics and generative mechanisms of software development productivity distributions Can An Old Fashioned Feature Extraction and A Light-weight Model Improve Vulnerability Type Identification Performance? Learning Test-Mutant Relationship for Accurate Fault Localisation
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1