[论文解读] Automatic generation of analysis class diagrams from use case specifications

Jitendra Singh Thakur, Atul Gupta|arXiv (Cornell University)|Aug 5, 2017

Software Engineering Research被引用 10

一句话总结

本文提出了一种基于自然语言处理技术的自动化方法，用于从自然语言用例规格自动生成准确且完整的分析类图。通过利用斯坦福NLP进行词性标注和类型依赖分析，应用句法结构规则与转换规则，该方法生成的类图在正确性、完整性和冗余性方面均优于现有自动化方法，这一结论通过受控实验得到验证。

ABSTRACT

In object oriented software development, the analysis modeling is concerned with the task of identifying problem level objects along with the relationships between them from software requirements. The software requirements are usually written in some natural language, and the analysis modeling is normally performed by experienced human analysts. The huge gap between the software requirements which are unstructured texts and analysis models which are usually structured UML diagrams, along with human slip-ups inevitably makes the transformation process error prone. The automation of this process can help in reducing the errors in the transformation. In this paper we propose a tool supported approach for automated transformation of use case specifications documented in English language into analysis class diagrams. The approach works in four steps. It first takes the textual specification of a use case as input, and then using a natural language parser generates type dependencies and parts of speech tags for each sentence in the specification. Then, it identifies the sentence structure of each sentence using a set of comprehensive sentence structure rules. Next, it applies a set of transformation rules on the type dependencies and parts of speech tags of the sentences to discover the problem level objects and the relationships between them. Finally, it generates and visualizes the analysis class diagram. We conducted a controlled experiment to compare the correctness, completeness and redundancy of the analysis class diagrams generated by our approach with those generated by the existing automated approaches. The results showed that the analysis class diagrams generated by our approach were more correct, more complete, and less redundant than those generated by the other approaches.

研究动机与目标

• 解决将非结构化的自然语言用例规格手动转换为结构化UML分析类图过程中易出错、耗时且不一致的问题。
• 通过自动化转换过程减少对人工干预和技能差异的依赖，提升分析建模的一致性。
• 通过最小化错误、缺失或冗余的模型元素，提升生成的分析类图的质量。
• 开发一种基于规则、工具支持的方法，利用自然语言处理技术实现可靠且可重复的模型生成。

提出的方法

• 输入：使用斯坦福NLP解析器对自然语言用例规格进行解析，提取词性（POS）标签和类型依赖（TDs）。
• 通过一套全面的规则分析句子结构，将句子分类为简单句、并列句、复杂句或并列复合句。
• 应用转换规则于词性标签和类型依赖，以识别领域级对象（类）、其属性、操作及关系。
• 基于语言模式和句法结构，识别类的构造型（如实体、边界、控制）以及关系类型（如关联、依赖）。
• 可视化模块根据提取的模型元素生成最终的分析类图。
• 通过受控实验评估该方法，对比现有自动化方法在正确性、完整性和冗余性方面的表现。

实验结果

研究问题

• RQ1 与现有自动化方法相比，所提出方法在多大程度上提升了自动生成的分析类图的正确性？
• RQ2 在模型元素（类、属性、操作、关系）的完整程度方面，所提出方法相较于其他自动化方法表现如何？
• RQ3 所提出方法在多大程度上减少了生成图中的冗余性（如多余的或错误的类和关系）？
• RQ4 所提出方法是否能在多种不同的用例规格中持续生成准确且语义合理的分析类图？

主要发现

• 所提出方法生成的分析类图在正确性方面显著优于现有自动化方法，正确性评分（包括类和关系）更高。
• 所提出方法在捕捉用例规格中必需的模型元素（包括属性、操作和关系）方面表现出更高的完整性。
• 该方法生成的类和关系更少，因此相比基线方法，图更简洁、更易于维护。
• 受控实验表明，所提出方法在正确性、完整性和冗余性减少三个评估维度上均优于现有自动化方法。