检索结果-内蒙古大学图书馆

Assisting engineers extracting requirements on components from domain documents

INFORMATION AND SOFTWARE TECHNOLOGY 2020年 118卷 106196-000页

作者： Lian, Xiaoli Liu, Wenchuang Zhang, Li Beihang Univ Beijing 100191 Peoples R China ByteDance Inc Beijing 100083 Peoples R China

Context When entering an unfamiliar domain, organizations usually have to invest significant time and effort performing domain analysis with the purpose of acquiring system requirements. This process usually involves collecting domain documents extensively, retrieving and reviewing the related ones carefully, searching for the requirements knowledge, then extracting and specifying system requirements. Furthermore, the task must often be performed repeatedly throughout the early phases of projects. Depending on the nature of the domain and the availability of documentation, this process is extremely time-consuming and may require non-trivial human effort. Objective: In order to assist engineers identifying requirements knowledge from a collect of domain documents, previously we proposed an approach MaRK in the Conference RE'16 which ranks the domain documents by their relevance to components and highlights the content that are likely to contain component-related information. Experiments showed MaRK can almost identify the top and bottom documents in the reference list. However, it tends to underestimate the relevance of the domain documents that have a number of sections with medium knowledge density. Method: We improve the ranking algorithm in MaRK and propose MaRK-H. In addition, to assist engineers locating the relevant information in lengthy documents, we preserve the highlighting work in MaRK and strengthen MaRK-II by extracting the summary of component-related text. MaRK-II is evaluated with the documents in three domains. Results: We found that MaRK-II significantly outperforms MaRK and VSM on ranking the documents by their relevance. And a user study showed that MaRK-II is indeed helpful for engineers to extract requirements on components. Conclusions: Our approach provides three mechanisms including documents ranking, pertinent content highlighting and summarizing to help engineers obtaining requirements from a collection of domain documents.

关键词： Requirements discovery domain reference model Documents ranking Extractive text summarization

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：