API comparison knowledge extraction via prompt-tuned language model

IF 1.7 3区 计算机科学 Q3 COMPUTER SCIENCE, SOFTWARE ENGINEERING Journal of Computer Languages Pub Date : 2023-06-01 DOI:10.1016/j.cola.2023.101200
Yangrui Yang, Yaping Zhu, Sisi Chen, Pengpeng Jian
{"title":"API comparison knowledge extraction via prompt-tuned language model","authors":"Yangrui Yang,&nbsp;Yaping Zhu,&nbsp;Sisi Chen,&nbsp;Pengpeng Jian","doi":"10.1016/j.cola.2023.101200","DOIUrl":null,"url":null,"abstract":"<div><p>Application Programming Interfaces (APIs) are frequent in software engineering domain texts, such as API references and Stack Overflow. These APIs and the comparison knowledge between them are not only important for solving programming issues (e.g., question answering), but they are also organized into structured knowledge to support many software engineering tasks (e.g., API misuse detection). As a result, extracting API comparison knowledge (API entities and semantic relations) from texts is essential. Existing rule-based and sequence labeling-based approaches must manually enumerate all linguistic patterns or label a large amount of data. Therefore, they involve a significant labor overhead and are exacerbated by morphological and common-word ambiguity. In contrast to matching or labeling API entities and relations, we formulates heterogeneous API extraction and API relation extraction tasks as a sequence-to-sequence generation task. It proposes APICKnow, an API entity-relation joint extraction model based on the large language model. To improve our model’s performance and quick learning ability, we adopt the prompt learning method to stimulate APICKnow to recognize API entities and relations. We systematically evaluate APICKnow on a set of sentences from Stack Overflow. The experimental results show that APICKnow can outperform the state-of-the-art baselines, and APICKnow has a quick learning ability and strong generalization ability.</p></div>","PeriodicalId":48552,"journal":{"name":"Journal of Computer Languages","volume":"75 ","pages":"Article 101200"},"PeriodicalIF":1.7000,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Computer Languages","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2590118423000102","RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"COMPUTER SCIENCE, SOFTWARE ENGINEERING","Score":null,"Total":0}
引用次数: 2

Abstract

Application Programming Interfaces (APIs) are frequent in software engineering domain texts, such as API references and Stack Overflow. These APIs and the comparison knowledge between them are not only important for solving programming issues (e.g., question answering), but they are also organized into structured knowledge to support many software engineering tasks (e.g., API misuse detection). As a result, extracting API comparison knowledge (API entities and semantic relations) from texts is essential. Existing rule-based and sequence labeling-based approaches must manually enumerate all linguistic patterns or label a large amount of data. Therefore, they involve a significant labor overhead and are exacerbated by morphological and common-word ambiguity. In contrast to matching or labeling API entities and relations, we formulates heterogeneous API extraction and API relation extraction tasks as a sequence-to-sequence generation task. It proposes APICKnow, an API entity-relation joint extraction model based on the large language model. To improve our model’s performance and quick learning ability, we adopt the prompt learning method to stimulate APICKnow to recognize API entities and relations. We systematically evaluate APICKnow on a set of sentences from Stack Overflow. The experimental results show that APICKnow can outperform the state-of-the-art baselines, and APICKnow has a quick learning ability and strong generalization ability.

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
API比较知识的快速语言模型提取
应用程序编程接口(API)经常出现在软件工程领域的文本中,如API引用和堆栈溢出。这些API和它们之间的比较知识不仅对于解决编程问题(例如,问题回答)很重要,而且它们还被组织成结构化知识,以支持许多软件工程任务(例如,API误用检测)。因此,从文本中提取API比较知识(API实体和语义关系)是必不可少的。现有的基于规则和序列标记的方法必须手动枚举所有语言模式或标记大量数据。因此,它们涉及大量的人工开销,并且由于形态和常用词的歧义而加剧。与匹配或标记API实体和关系相反,我们将异构的API提取和API关系提取任务定义为序列到序列生成任务。提出了基于大型语言模型的API实体关系联合提取模型APICKnow。为了提高模型的性能和快速学习能力,我们采用即时学习方法来刺激APICKnow识别API实体和关系。我们在Stack Overflow的一组句子上系统地评估APICKnow。实验结果表明,APICKnow可以优于最先进的基线,并且具有快速的学习能力和较强的泛化能力。
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 去求助
来源期刊
Journal of Computer Languages
Journal of Computer Languages Computer Science-Computer Networks and Communications
CiteScore
5.00
自引率
13.60%
发文量
36
期刊最新文献
Debugging in the Domain-Specific Modeling Languages for multi-agent systems GPotion: Embedding GPU programming in Elixir Near-Pruned single assignment transformation of programs MLAPW: A framework to assess the impact of feature selection and sampling techniques on anti-pattern prediction using WSDL metrics Editorial Board
×
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