基于句法分析的代码摘要技术

doi:10.11772/j.issn.1001-9081.2015.07.1999

计算机应用 ›› 2015, Vol. 35 ›› Issue (7): 1999-2003.DOI: 10.11772/j.issn.1001-9081.2015.07.1999

基于句法分析的代码摘要技术

王金水¹, 薛醒思¹, 翁伟²

1. 福建工程学院信息科学与工程学院, 福州 350108;
2. 厦门理工学院计算机与信息工程学院, 福建厦门 361024

收稿日期:2015-01-21 修回日期:2015-03-27 出版日期:2015-07-10 发布日期:2015-07-17
通讯作者: 王金水(1981-),男,福建漳州人,讲师,博士,CCF会员,主要研究方向:软件工程、大数据分析,wangjinshui@fjut.edu.cn
作者简介:薛醒思(1981-),男,福建福清人,讲师,博士,CCF会员,主要研究方向:进化算法; 翁伟(1979-),男,湖南衡阳人,讲师,硕士,CCF会员,主要研究方向:数据挖掘。
基金资助:
国家自然科学基金资助项目(61402108);福建省中青年教师教育科研资助项目(JA14221);福建工程学院科研启动基金资助项目(GY-Z13113; GY-Z14068)。

Source code summarization technology based on syntactic analysis

WANG Jinshui¹, XUE Xingsi¹, WENG Wei²

1. College of Information Science and Engineering, Fujian University of Technology, Fuzhou Fujian 350108, China;
2. College of Computer and Information Engineering, Xiamen University of Technology, Xiamen Fujian 361024, China

Received:2015-01-21 Revised:2015-03-27 Online:2015-07-10 Published:2015-07-17

摘要/Abstract

摘要：

针对词袋模型忽略了词条之间语义关系和概念结构的问题,提出一种基于句法分析的代码摘要技术。首先,该技术利用词性标注识别出最有可能体现代码特性的关键词;然后,通过块分析修正在词性标注过程中可能引入的错误;其次,对标识出的关键词进行降噪,以减少文本噪声带来的不利影响;最后,从关键词中选取若干个权值最高的词以组成代码摘要。实验结果表明,与基于词频-逆文档频率(TF-IDF)和基于TF-IDF扩展的代码摘要技术对比,所提技术生成的代码摘要与参考答案的重叠率(overlap)至少分别提高了9%和6%,说明该技术能够生成更加准确的代码摘要。

关键词: 代码摘要, 文本摘要, 句法分析, 自然语言处理, 程序理解

Abstract:

For overcoming the drawback of ignoring the semantic relationship between terms and concept structure in the bag of words model, a source code summarization technology based on syntactic analysis was proposed. Firstly, the part-of-speech tagging was utilized to recognize the keywords that characterized the code feature most. Secondly, the chunk parsing was used to revise the errors that could be introduced in the process of part-of-speech tagging. Thirdly, the noise reduction for those keywords was carried out to decrease the influence of text noise. Finally, several keywords with highest weights were selected to compose the summaries. Through the comparison with TF-IDF (Term Frequency-Inverse Document Frequency)-based and extended TF-IDF-based source code summarization technologies in the experiment, with respect to the overlap coefficient of the golden set, the summaries obtained by the proposed technology are improved by at least 9% and 6% respectively, which illuminates that the proposed technology is able to generate more precise source code summaries.

Key words: source code summarization, text summarization, syntactic analysis, natural language processing, program comprehension

中图分类号:

TP311.5

王金水, 薛醒思, 翁伟. 基于句法分析的代码摘要技术[J]. 计算机应用, 2015, 35(7): 1999-2003.

WANG Jinshui, XUE Xingsi, WENG Wei. Source code summarization technology based on syntactic analysis[J]. Journal of Computer Applications, 2015, 35(7): 1999-2003.

参考文献

[1] EDDY B P, ROBINSON J A, KRAFT N A, et al. Evaluating source code summarization techniques: replication and expansion [C]// ICPC 2013: Proceedings of the 2013 IEEE 21st International Conference on Program Comprehension. Piscataway: IEEE, 2013: 13-22.
[2] LATOZA T D, VENOLIA G, DELINE R. Maintaining mental models: a study of developer work habits [C]// ICSE 2006: Proceedings of the 2006 International Conference on Software Engineering. New York: ACM, 2006: 492-501.
[3] KO A J, MYERS B A, COBLENZ M J, et al. An exploratory study of how developers seek, relate, and collect relevant information during software maintenance tasks [J]. IEEE Transactions on Software Engineering. 2006, 32(12): 971-987.
[4] MORENO L, APONTE J, SRIDHARA G, et al. Automatic generation of natural language summaries for Java classes [C]// ICPC 2013: Proceedings of the 2013 IEEE 21st International Conference on Program Comprehension. Piscataway: IEEE, 2013: 23-32.
[5] HAIDUC S, APONTE J, MORENO L, et al. On the use of automated text summarization techniques for summarizing source code [C]// WCRE 2010: Proceedings of the 2010 17th Working Conference on Reverse Engineering. Piscataway: IEEE, 2010: 35-44.
[6] McBURNEY P W, LIU C, McMILLAN C, et al. Improving topic model source code summarization [C]// ICPC 2014: Proceedings of the 2014 22nd International Conference on Program Comprehension. New York: ACM, 2014: 291-294.
[7] KAJKO-MATTSSON M. A survey of documentation practice within corrective maintenance [J]. Empirical Software Engineering, 2005, 10(1): 31-55.
[8] SAHARIA N, SHARMA U, KALITA J. A suffix-based noun and verb classifier for an inflectional language [C]// IALP 2010: Proceedings of the 2010 International Conference on Asian Language Processing. Piscataway: IEEE, 2010: 19-22.
[9] JURAFSKY D, MARTIN J H. Speech and language processing: an introduction to natural language processing, computational linguistics, and speech recognition [M]. Upper Saddle River: Prentice Hall, 2000: 139-141.
[10] CAPOBIANCO G, de LUCIA A, OLIVETO R, et al. Improving IR-based traceability recovery via noun-based indexing of software artifacts [J]. Journal of Software: Evolution and Process, 2013, 25(7): 743-762.
[11] FRY Z P, SHEPHERD D, HILL E, et al. Analysing source code: looking for useful verb-direct object pairs in all the right places [J]. IET Software, 2008, 2(1): 27-36.
[12] CAPOBIANCO G, de LUCIA A, OLIVETO R, et al. On the role of the nouns in IR-based traceability recovery [C]// ICPC 2009: Proceedings of the 2009 IEEE 17th International Conference on Program Comprehension. Piscataway: IEEE, 2009: 148-157.
[13] ZAMANI S, LEE S P, SHOKRIPOUR R, et al. A noun-based approach to feature location using time-aware term-weighting [J]. Information and Software Technology, 2014, 56(8): 991-1011.
[14] RODEGHERO P, McMILLAN C, McBURNEY P W, et al. Im-proving automated source code summarization via an eye-tracking study of programmers [C]// ICSE 2014: Proceedings of the 2014 36th International Conference on Software Engineering. New York: ACM, 2014: 390-401.
[15] WANG J, WU G, ZHOU Y, et al. Research on automatic summarization of Web document guided by discourse [J]. Journal of Computer Research and Development, 2003, 40(3): 398-405.(王继成,武港山,周源远,等.一种篇章结构指导的中文Web文档自动摘要方法[J].计算机研究与发展,2003,40(3):398-405.)
[16] SHEPHERD D, FRY Z P, HILL E, et al. Using natural language program analysis to locate and understand action-oriented concerns [C]// AOSD 2007: Proceedings of the 2007 6th International Conference on Aspect-Oriented Software Development. New York: ACM, 2007: 212-224.

基于句法分析的代码摘要技术

Source code summarization technology based on syntactic analysis

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	谢德峰, 吉建民. 融入句法感知表示进行句法增强的语义解析[J]. 计算机应用, 2021, 41(9): 2489-2495.
[2]	刘雅璇, 钟勇. 基于头实体注意力的实体关系联合抽取方法[J]. 计算机应用, 2021, 41(9): 2517-2522.
[3]	周险兵, 樊小超, 任鸽, 杨勇. 基于多层次语义特征的英文作文自动评分方法[J]. 计算机应用, 2021, 41(8): 2205-2211.
[4]	李想, 王卫兵, 尚学达. 指针生成网络和覆盖损失优化的Transformer在生成式文本摘要领域的应用[J]. 计算机应用, 2021, 41(6): 1647-1651.
[5]	李文惠, 曾上游, 王金金. 基于改进注意力机制的图像描述生成算法[J]. 计算机应用, 2021, 41(5): 1262-1267.
[6]	王朱君, 王石, 李雪晴, 朱俊武. 基于深度学习的事件因果关系抽取综述[J]. 计算机应用, 2021, 41(5): 1247-1255.
[7]	李雪晴, 王石, 王朱君, 朱俊武. 自然语言生成综述[J]. 计算机应用, 2021, 41(5): 1227-1235.
[8]	刘睿珩, 叶霞, 岳增营. 面向自然语言处理任务的预训练模型综述[J]. 计算机应用, 2021, 41(5): 1236-1246.
[9]	杨璐, 何明祥. 基于门控机制和卷积神经网络的中文文本情感分析模型[J]. 计算机应用, 2021, 41(10): 2842-2848.
[10]	杨国峰, 杨勇. 基于BERT的常见作物病害问答系统问句分类[J]. 计算机应用, 2020, 40(6): 1580-1586.
[11]	赵亚欧, 张家重, 李贻斌, 付宪瑞, 生伟. 融合基于语言模型的词嵌入和多尺度卷积神经网络的情感分析[J]. 计算机应用, 2020, 40(3): 651-657.
[12]	黄友文, 游亚东, 赵朋. 融合卷积注意力机制的图像描述生成模型[J]. 计算机应用, 2020, 40(1): 23-27.
[13]	陈志豪, 余翔, 刘子辰, 邱大伟, 顾本刚. 基于注意力和字嵌入的中文医疗问答匹配方法[J]. 计算机应用, 2019, 39(6): 1639-1645.
[14]	严红, 陈兴蜀, 王文贤, 王海舟, 殷明勇. 基于深度神经网络的法语命名实体识别模型[J]. 计算机应用, 2019, 39(5): 1288-1292.
[15]	张克君, 李伟男, 钱榕, 史泰猛, 焦萌. 基于深度学习的文本自动摘要方案[J]. 计算机应用, 2019, 39(2): 311-315.