SHF: Medium: Principled Co-Reasoning of Software and Natural-Language Artifacts

SHF：媒介：软件和自然语言制品的原则性共同推理

• 批准号: 1901242
• 负责人: Lin Tan
• 金额: $ 90万
• 依托单位: Purdue University
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2019
• 资助国家: 美国
• 起止时间: 2019-07-15 至 2025-06-30
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1901242&HistoricalAwards=false
• 关键词: SHF; Medium; Principled; Co; Reasoning

Software is pervasive. Software typically contains a large volume of artifacts written in natural languages (NL), including code comments, change logs, manual pages, constant strings in code, and variable and function names. Software NL artifacts contain a wealth of semantic information that is often missing in code artifacts. There has been substantial existing work on analyzing NL artifacts and leveraging them in a wide range of software-engineering applications. However, most existing work is ad hoc, and is limited in its generality. Existing work typically considers NL artifacts as sources for additional information instead of first-class objects on which analysis operates (like variable types in program analysis), missing the opportunity to take full advantage of software NL artifacts. Thus, this project develops co-analysis of code and NL artifacts, which treats NL artifacts as first-class objects. In addition to advancing the state of the art, the principles, infrastructure, and techniques developed in the project are transformative, providing educational and practical tools to generate high-quality source code and software documents. These techniques improve program analysis, software maintenance, software reliability, and engineering productivity, for lower software development cost and better work and recreational lives, where software is indispensable.The project develops a principled and sophisticated software reasoning method that couples NL analysis and program analysis. It automatically models and classifies various kinds of NL artifacts, and attributes them to the related code elements. As such, they become first-class objects just like other classic objects in program analysis (e.g., variables and statements). They can be inferred, propagated, updated, associated, and formally reasoned about, to maximize the utilization of their rich semantics (e.g., comments can be propagated to code elements that are not previously commented through program analysis). The project activities include (1) modeling, classifying, and attributing NL artifacts, through developing domain-specific language models to process, model, classify NL artifacts and attribute them to the corresponding code elements, (2) building uniform representation, propagation, and co-reasoning of NL artifacts and code artifacts, (3) producing highly accurate and scalable probabilistic inference, by leveraging probabilistic graph models to perform the uniform reasoning of both code and NL artifacts, and (4) exploring new applications of co-analysis in domains including software testing.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

软件无处不在。软件通常包含大量用自然语言 (NL) 编写的工件，包括代码注释、更改日志、手册页、代码中的常量字符串以及变量和函数名称。 软件 NL 工件包含大量在代码工件中经常缺失的语义信息。 现有大量工作致力于分析 NL 工件并在广泛的软件工程应用中利用它们。 然而，大多数现有工作都是临时性的，其通用性有限。 现有的工作通常将 NL 工件视为附加信息的来源，而不是分析操作的一流对象（如程序分析中的变量类型），从而错过了充分利用软件 NL 工件的机会。因此，该项目开发了代码和 NL 工件的协同分析，将 NL 工件视为一流对象。 除了推进最先进的技术之外，该项目中开发的原理、基础设施和技术也具有变革性，提供教育和实用工具来生成高质量的源代码和软件文档。这些技术提高了程序分析、软件维护、软件可靠性和工程生产率，以降低软件开发成本并改善工作和娱乐生活，而软件是不可或缺的。该项目开发了一种原则性的、复杂的软件推理方法，将自然语言分析和程序分析结合起来。 。它自动对各种 NL 工件进行建模和分类，并将它们归因于相关的代码元素。因此，它们成为一流的对象，就像程序分析中的其他经典对象（例如变量和语句）一样。它们可以被推断、传播、更新、关联​​和形式推理，以最大限度地利用它们丰富的语义（例如，注释可以传播到之前没有通过程序分析注释的代码元素）。项目活动包括 (1) 建模、分类和归因 NL 工件，通过开发特定领域的语言模型来处理、建模、分类 NL 工件并将其归因于相应的代码元素，(2) 构建统一的表示、传播和属性NL 工件和代码工件的共同推理，(3) 通过利用概率图模型对代码和 NL 工件执行统一推理，生成高度准确且可扩展的概率推理，以及 (4) 探索新的该奖项反映了 NSF 的法定使命，并通过使用基金会的智力价值和更广泛的影响审查标准进行评估，被认为值得支持。

项目成果

RULER: discriminative and iterative adversarial training for deep neural network fairness

RULER：深度神经网络公平性的判别性和迭代对抗性训练

• DOI: 10.1145/3540250.3549169
• 发表时间: 2022-11-07
• 期刊: Proceedings of the 30th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering
• 作者: Guanhong Tao;Weisong Sun;Tingxu Han;Chunrong Fang;Xiangyu Zhang
• 通讯作者: Xiangyu Zhang

Constrained Optimization with Dynamic Bound-scaling for Effective NLP Backdoor Defense

通过动态边界缩放进行约束优化，实现有效的 NLP 后门防御

• 发表时间: 2022-01
• 期刊: Proceedings of the 39th International Conference on Machine Learning,
• 作者: Guangyu Shen;Yingqi Liu;Guanhong Tao;Qiuling Xu;Zhuo Zhang;Shengwei An;Shiqing Ma;Xiangyu Zhang
• 通讯作者: Xiangyu Zhang

Vicious Cycles in Distributed Software Systems

分布式软件系统的恶性循环

• DOI: 10.1109/ase56229.2023.00032
• 发表时间: 2023-09-11
• 期刊: 2023 38th IEEE/ACM International Conference on Automated Software Engineering (ASE)
• 作者: Shangshu Qian;Wen Fan;Lin Tan;Yongle Zhang
• 通讯作者: Yongle Zhang

C2S: translating natural language comments to formal program specifications

C2S：将自然语言注释翻译为正式的程序规范

• DOI: 10.1145/3368089.3409716
• 发表时间: 2020-11-07
• 期刊: Proceedings of the 28th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering
• 作者: Juan Zhai;Yu Shi;Minxue Pan;Guian Zhou;Yongxiang Liu;Chunrong Fang;Shiqing Ma;Lin Tan;X. Zhang
• 通讯作者: X. Zhang

CPC: automatically classifying and propagating natural language comments via program analysis

CPC：通过程序分析自动分类和传播自然语言评论

• DOI: 10.1145/3377811.3380427
• 发表时间: 2020-06
• 期刊: Proceedings of the ACM/IEEE 42nd International Conference on Software Engineering
• 作者: Zhai, Juan;Xu, Xiangzhe;Shi, Yu;Tao, Guanhong;Pan, Minxue;Ma, Shiqing;Xu, Lei;Zhang, Weifeng;Tan, Lin;Zhang, Xiangyu
• 通讯作者: Zhang, Xiangyu