Guiding peer-feedback in learning software design using UML

Rukmono, Satrio Adi; Chaudron, Michel R. V.

doi:10.1145/3510456.3514148

Cited by 2 publications

(3 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Information extraction and text mining in technical domains such as software engineering and security have been explored to benefit domain-specific applications such as technical question answering (Yu et al 2020(Yu et al , 2021, knowledge graph construction (Rukmono and Chaudron 2023), and code recommendation (Jin et al 2023). For named entity recognition (NER) in technical domains, Ye et al (2016) show that conditional random fields can outperform traditional rule-based models; Tabassum et al (2020) further leverage the power of PLMs and achieve better performance on StackOverflow and GitHub; Lopez et al (2021) find that the layout information from raw PDFs can help capture document structure for better NER performance.…”

Section: Text Mining In Technical Domainsmentioning

confidence: 99%

“…First, fine-grained entity typing is critical for domain-specific applications. For example, in software and security domains (e.g., StackOverflow threads, GitHub README files, and vulnerability descriptions), entities need to be typed in fine-grained scale (e.g., devices, operating systems, versions, and functions) in order to drive downstream applications (e.g., technical question answering (Yu et al 2020(Yu et al , 2021 and knowledge graph construction (Rukmono and Chaudron 2023)).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Seed-Guided Fine-Grained Entity Typing in Science and Engineering Domains

Zhang,

Shen

et al. 2024

AAAI

View full text Add to dashboard Cite

Accurately typing entity mentions from text segments is a fundamental task for various natural language processing applications. Many previous approaches rely on massive human-annotated data to perform entity typing. Nevertheless, collecting such data in highly specialized science and engineering domains (e.g., software engineering and security) can be time-consuming and costly, without mentioning the domain gaps between training and inference data if the model needs to be applied to confidential datasets. In this paper, we study the task of seed-guided fine-grained entity typing in science and engineering domains, which takes the name and a few seed entities for each entity type as the only supervision and aims to classify new entity mentions into both seen and unseen types (i.e., those without seed entities). To solve this problem, we propose SEType which first enriches the weak supervision by finding more entities for each seen type from an unlabeled corpus using the contextualized representations of pre-trained language models. It then matches the enriched entities to unlabeled text to get pseudo-labeled samples and trains a textual entailment model that can make inferences for both seen and unseen types. Extensive experiments on two datasets covering four domains demonstrate the effectiveness of SEType in comparison with various baselines. Code and data are available at: https://github.com/yuzhimanhua/SEType.

show abstract

Section: Text Mining In Technical Domainsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Seed-Guided Fine-Grained Entity Typing in Science and Engineering Domains

Zhang,

Shen

et al. 2024

AAAI

View full text Add to dashboard Cite

show abstract

“…2. Targeted Feedback: One of the most prevalent forms of learning-oriented support during a hackathon is the inclusion of mentor or peer feedback opportunities, especially when the mentors perceive their role as that of a traditional (workplace or educational) mentor (Nolte et al, 2020a;Rukmono and Chaudron, 2022). The organization of feedback should encourage ample mentor-team interactions.…”

Section: Interventions (Mode Of Delivery)mentioning

confidence: 99%

IoT Security Risk Management: A Framework and Teaching Approach

Affia¹,

Nolte²,

Matulevičius³

2023

Informatics in Education

View full text Add to dashboard Cite

While Internet of Things (IoT) devices have increased in popularity and usage, their users have become more susceptible to cyber-attacks, thus emphasizing the need to manage the resulting security risks. However, existing works reveal research gaps in IoT security risk management frameworks where the IoT architecture – building blocks of the system – are not adequately considered for analysis. Also, security risk management includes complex tasks requiring appropriate training and teaching methods to be applied effectively. To address these points, we first proposed a security risk management framework that captures the IoT architecture perspective as an input to further security risk management activities. We then proposed a hackathon learning model as a practical approach to teach hackathon participants to apply the IoT security risk management framework. To evaluate the benefits of the framework and the hackathon learning model, we conducted an action research study that integrated the hackathon learning model into a cybersecurity course, where students learn how to apply the framework. Our findings show that the IoT-ARM framework was beneficial in guiding students towards IoT security risk management and producing repeatable outcomes. Additionally, the study demonstrated the applicability of the hackathon model and its interventions in supporting the learning of IoT security risk management and applying the proposed framework to real-world scenarios.

show abstract

Guiding peer-feedback in learning software design using UML

Cited by 2 publications

References 8 publications

Seed-Guided Fine-Grained Entity Typing in Science and Engineering Domains

Seed-Guided Fine-Grained Entity Typing in Science and Engineering Domains

IoT Security Risk Management: A Framework and Teaching Approach

Contact Info

Product

Resources

About