I-Corps: Fragmented Learning App based on Knowledge Graphs

I-Corps：基于知识图谱的碎片化学习应用

• 批准号: 2034508
• 负责人: LiGuo Huang
• 金额: $ 5万
• 依托单位: Southern Methodist University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-08-01 至 2023-01-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2034508&HistoricalAwards=false
• 关键词: Corps; Fragmented; Learning; App; based

The broader impact/commercial potential of this I-Corps project is the development of a Fragmented Learning App based on knowledge graphs to improve the effectiveness and efficiency of fragmented learning as a complement to the traditional collective learning in the classroom setting. This goal is to examine the impact of the fragmented learning style on various types of domain knowledge versus the (predominantly used) collective learning style. The proposed technology will explore how knowledge graphs may represent and organize knowledge (e.g., concepts, theorems, principles, rules) in various domains and enable knowledge reasoning and derivation. Data from various types of users will be collected to enrich and evolve the knowledge graphs based on the latest learning needs.This I-Corps project is based on the development of technology to support fragmented learning, which allows users to study anytime and anywhere as well as on various platform, improving their learning effectiveness and efficiency. Specially, the proposed technology is designed by integrating knowledge graphs with machine/deep learning and Natural Language Processing models to recommend relevant learning materials based on coherent and evolving knowledge graphs rather than user-constructed keyword search. The app constructs both a complete knowledge graph for a knowledge domain and a personalized knowledge graph for the individual user to generate a personalized learning plan adapted to his/her individual learning needs. Leveraging knowledge graphs to represent and organize knowledge from big data sources (text and video tutorials), the Fragmented Learning App captures explicit and implicit relations of knowledge and derives new knowledge and relations to prevent fragmenting the domain knowledge. In addition, the technology incorporates the social platform and observer roles for user interaction and knowledge exchange.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.

I-Corps项目更广泛的影响/商业潜力是开发基于知识图谱的碎片化学习应用程序，以提高碎片化学习的有效性和效率，作为对课堂环境中传统集体学习的补充。这个目标是考察碎片化的学习风格对各种类型的领域知识的影响与(主要使用的)集体学习风格的影响。提出的技术将探索知识图如何表示和组织各个领域的知识(例如，概念、定理、原则、规则)，并使知识推理和推导成为可能。这个i-Corps项目基于支持碎片化学习的技术的发展，允许用户随时随地以及在不同的平台上进行学习，提高了他们的学习效果和效率。特别是，该技术通过将知识图与机器/深度学习和自然语言处理模型相结合，基于连贯和不断演变的知识图来推荐相关学习材料，而不是基于用户构建的关键字搜索。该应用程序既为知识领域构建了完整的知识图谱，又为个人用户构建了个性化知识图谱，以生成适合他/她个人学习需求的个性化学习计划。碎片化学习应用利用知识图来表示和组织来自大数据来源(文本和视频教程)的知识，捕获知识的显性和隐性关系，并派生新的知识和关系，以防止领域知识碎片化。此外，该技术结合了社交平台和观察者角色，用于用户互动和知识交流。该奖项反映了NSF的法定使命，并通过使用基金会的智力优势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

The ABLoTS Approach for Bug Localization: is it replicable and generalizable?

• DOI: 10.1109/msr59073.2023.00083
• 发表时间: 2023-05
• 期刊: 2023 IEEE/ACM 20th International Conference on Mining Software Repositories (MSR)
• 作者: Feifei Niu;Christoph Mayr-Dorn;W. K. Assunção;LiGuo Huang;Jidong Ge;Bin Luo;Alexander Egyed

Machine/Deep Learning for Software Engineering: A Systematic Literature Review

• DOI: 10.1109/tse.2022.3173346
• 发表时间: 2023-03
• 期刊: IEEE Transactions on Software Engineering
• 影响因子: 7.4
• 作者: Simin Wang;LiGuo Huang;Amiao Gao;Jidong Ge;Tengfei Zhang;Haitao Feng;Ishna Satyarth;Ming Li-Ming

AST-Trans: Code Summarization with Efficient Tree-Structured Attention

• DOI: 10.1145/3510003.3510224
• 发表时间: 2022-05
• 期刊: 2022 IEEE/ACM 44th International Conference on Software Engineering (ICSE)
• 作者: Ze Tang;Xiaoyu Shen;Chuanyi Li;Jidong Ge;LiGuo Huang;Zheling Zhu;Bin Luo

SPT-Code: Sequence-to-Sequence Pre-Training for Learning Source Code Representations

• DOI: 10.1145/3510003.3510096
• 发表时间: 2022-01
• 期刊: 2022 IEEE/ACM 44th International Conference on Software Engineering (ICSE)
• 作者: Changan Niu;Chuanyi Li;Vincent Ng;Jidong Ge;LiGuo Huang;B. Luo

RAT: A Refactoring-Aware Traceability Model for Bug Localization

• DOI: 10.1109/icse48619.2023.00028
• 发表时间: 2023-05
• 期刊: 2023 IEEE/ACM 45th International Conference on Software Engineering (ICSE)
• 作者: Feifei Niu;W. K. Assunção;LiGuo Huang;Christoph Mayr-Dorn;Jidong Ge;Bin Luo;Alexander Egyed