Page Not Found
Page not found. Your pixels are in another canvas.
A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.
Page not found. Your pixels are in another canvas.
About me
This is a page not in th emain menu
Published:
This post will show up by default. To disable scheduling of future posts, edit config.yml
and set future: false
.
Published:
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
Published:
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
Published:
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
Published:
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
Published in CIKM, 2018
Recommended citation: Tien-Hsuan Wu, Zhiyong Wu, Ben Kao, and Pengcheng Yin. Towards practical open knowledge base canonicalization. In Proceedings of the 27th ACM International Conference on Information and Knowledge Management, pages 883-892. ACM, 2018. https://dl.acm.org/doi/10.1145/3269206.3271707
Published in WSDM, 2020
Recommended citation: Zhiyong Wu, Ben Kao, Tien-Hsuan Wu, Pengcheng Yin, Qun Liu. PERQ: Predicting, Explaining, and Rectifying Failed Questions in KB-QA Systems. Proceedings of the 13th International Conference on Web Search and Data Mining, pages 663-671. ACM, 2020. https://dl.acm.org/doi/abs/10.1145/3336191.3371782
Published in WSDM, 2020
Recommended citation: Tien-Hsuan Wu, Ben Kao, Zhiyong Wu, Xiyang Feng, Qianli Song, Cheng Chen. MULCE: Multi-level Canonicalization with Embeddings of Open Knowledge Bases. Web Information Systems Engineering – WISE 2020. Lecture Notes in Computer Science, pages 315-327. Springer, 2020. https://dl.acm.org/doi/abs/10.1145/3336191.3371782
Published in JURIX, 2020
Recommended citation: Tien-Hsuan Wu, Ben Kao, Anne SY Cheung, Michael MK Cheung, Chen Wang, Yongxi Chen, Guowen Yuan and Reynold Cheng. Integrating Domain Knowledge in AI-assisted Criminal Sentencing of Drug Trafficking Cases. In Legal Knowledge and Information Systems: JURIX 2020: The Thirty-third Annual Conference, Brno, Czech Republic, December 9-11, 2020 (Vol. 334, p. 174). IOS Press. https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA200861
Published in JURIX, 2021
Recommended citation: Tien-Hsuan Wu, Ben Kao, Felix Chan, Anne SY Cheung, Michael MK Cheung, Guowen Yuan and Yongxi Chen. Semantic Search and Summarization of Judgments Using Topic Modeling. In Legal Knowledge and Information Systems: JURIX 2021: The Thirty-fourth Annual Conference, Vilnius, Lithuania, 8-10 December 2021 (Vol. 346, p. 100). IOS Press. https://ebooks.iospress.nl/doi/10.3233/FAIA210323
Published in JURIX, 2022
Recommended citation: Tien-Hsuan Wu, Ben Kao, Henry Chan and Michael MK Cheung. Judgment Tagging and Recommendation Using Pre-trained Language Models and Legal Taxonomy. In Legal Knowledge and Information Systems: JURIX 2022: The Thirty-fifth Annual Conference, Saarbrücken, Germany, 14-16 December 2022 (Vol. 362, p. 255). IOS Press. https://ebooks.iospress.nl/doi/10.3233/FAIA220476
Published in AAAI, 2023
Recommended citation: Guowen Yuan, Ben Kao and Tien-Hsuan Wu. CEMA–Cost-Efficient Machine-Assisted Document Annotations. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 37, No. 9, pp. 11043-11050).
Published in Artificial Intelligence and Law, 2023
Recommended citation: Mingruo Yuan, Ben Kao, Tien-Hsuan Wu, Michael M. K. Cheung, Henry W. H. Chan, Anne S. Y. Cheung, Felix W. H. Chan and Yongxi Chen. Bringing legal knowledge to the public by constructing a legal question bank using large-scale pre-trained language model. Artificial Intelligence and Law, 1-37.
Published in JURIX, 2023
Recommended citation: Tien-Hsuan Wu, Ben Kao and Michael MK Cheung. Judgment Retrieval Made Easier Through Query Analysis. In Legal Knowledge and Information Systems: JURIX 2023: The Thirty-sixth Annual Conference, Maastricht, Netherlands, 18–20 December 2023 (Vol. 379, p. 299). IOS Press. https://ebooks.iospress.nl/doi/10.3233/FAIA230978
Published in JURIX, 2024
Recommended citation: Titus T.H. Ng, Tien-Hsuan Wu, Benjamin Minhao Chen, Yongxi Chen and Ben Kao. A Multi-Stage Prompting and RAG Approach to Generating Legal Analysis in Common Law Systems. In Legal Knowledge and Information Systems: JURIX 2024: The Thirty-seventh Annual Conference, Brno, Czech Republic, 11–13 December 2024 (Vol. 395, p. 387). IOS Press. https://ebooks.iospress.nl/doi/10.3233/FAIA241278
Published in ASEE Annual Conference, 2025
The rise of Large Language Models and other artificial intelligence (AI) technologies has sparked significant interest among students and industrial employers. Consequently, there is a growing need for academic makerspaces to incorporate AI elements-such as AI-powered chatbots and robotics. These AI-related practical experiences are expected to complement the theoretical knowledge acquired in the classroom for computer science (CS) students, while also providing foundational exposure for students from other engineering disciplines. However, many makerspaces, even within universities, face substantial challenges in adapting to this rapidly evolving landscape. To address this challenge, this paper presents an experiential learning framework implemented in a university’s student innovation center and makerspace from June 2023 to December 2024. This framework is designed to accommodate students from various fields, effectively integrating AI elements into the ir extracurricular activities in the makerspace. Specifically, we adopt a project-based learning approach that invites students with either technical backgrounds or professional training related to the problems being tackled. For example, we assembled teams of CS students and social work students to develop a chatbot for interactive coaching of social workers. Recognizing that AI applications extend beyond chatbots, we encourage exploration of diverse topics (e.g., AI and robotics), seamlessly integrating AI elements into the traditional focus areas of makerspaces. For students with limited experience, a series of hands-on workshops were carefully designed, starting from foundational concepts in training a neural network to more practical experience of building their own chatbots. These series of workshops are expected to progressively build up their skills for involving in or initiating AI-related innovations. We have also made the teaching materials of the workshops publicly available to our makerspace community. In addition to the educational content, computing facilities are a significant concern for many makerspaces, as AI-related projects often require substantial computational resources. To address this, we devised a cost-effective strategy for establishing the necessary facilities to support these activities. While high-performance computing workstations may be essential for some real-world projects, cloud services can be leveraged to facilitate hands-on workshops, providing scalable resources without the need for significant investment. To assess the effectiveness of our proposed framework, we have collected and analyzed post-workshop surveys. Additionally, we invited students working on projects to reflect on their learning experiences, providing qualitative insights to our designed framework. We position our makerspace within the classification system proposed by Wilczynski (2017) to facilitate comparisons with other university makerspaces in terms of resources. Surveying feedback were reported, which demonstrates the preliminary effectiveness of the proposed framework and highlight both the successes and the challenges. We hope this initial discussion on integrating AI into makerspaces will be inspiring to other institutions to respond to the shifting demands of the AI era.
Recommended citation: Lei Yang, Tien-Hsuan Wu, Chun Kit Chui and Chun Kit Chan. Equipping Academic Makerspaces with Artificial Intelligence Elements. 2025 ASEE Annual Conference.
Published in ASEE Annual Conference, 2025
This practice paper discusses the design, implementation, and outcomes of an overseas team-building program organized by the Tam Wing Fan Innovation Wing (HKU Innovation Wing) at the University of Hong Kong. Established in December 2020, the center has actively supported Student-Initiated Interest Groups (SIGs) focused on technology exploration and development among undergraduate students. In the 2023-2024 academic year, the center had expanded to accommodate 22 active SIGs with over 300 student participants, fostering an interdisciplinary, project-based, hands-on learning culture within the University of Hong Kong. Despite the growth of SIGs, several issues have surfaced. Primarily, silos exist among the SIGs, hindering effective interactions and collaboration. Additionally, some SIGs have started contending for resources, particularly project space, leading to escalated conflicts. Moreover, a redundancy in training topics among various SIGs for new members has been noted, resulting in duplicated workloads for newcomers. In the 2024-25 academic year, we implemented an overseas team-building program for student leaders to address these challenges. Following the Tuckman Team Model, we introduced five incentives to boost engagement. The program aims to unite leaders into a cohesive ambassador team, enhancing their understanding of academic makerspaces’ educational value. By immersing them in global makerspace activities, they learn best leadership practices to bring back and foster a collaborative culture within the Innovation Wing. In September 2024, fourteen leaders representing seven SIGs took part in the pilot program. They engaged in ice-breaking activities to dismantle silos, brainstorming sessions to strategize how their SIGs could enhance the HKU Innovation Wing, goal-setting discussions to define outcomes for their involvement in an overseas makerspace symposium, presentations to share their insights, and knowledge-sharing sessions to disseminate experiences and conclusions to other makerspace members. Surveys and analysis of written reflections from the team leaders indicate that the overseas team-building program effectively dismantled silos, enhanced collaboration, and promoted personal growth among student leaders. These leaders showcased a shift in perspective when offering recommendations for the improvement of the Innovation Wing. Comparing them with the 2023/24 cohort of leaders, these individuals displayed a more proactive approach to enhancing the overall functionality and effectiveness of the makerspace for one another, rather than solely focusing on the benefits of their individual SIGs.
Recommended citation: Chun Kit Chui, Match Wai Lun Ko, Kei Yiu Mo, Chun Kit Chan, Lei Yang and Tien-Hsuan Wu. Overseas Team Building for Student Leaders in Academic Makerspaces. 2025 ASEE Annual Conference.
Published in IJCAI, 2025
Recommended citation: Mingruo Yuan, Ben Kao and Tien-Hsuan Wu. QBR - A Question-Bank-Based Approach to Fine-Grained Legal Knowledge Retrieval for the General Public. In IJCAI 2025. https://www.arxiv.org/abs/2505.04883
Undergraduate course, University 1, Department, 2014
This is a description of a teaching experience. You can use markdown like any other post.
Workshop, University 1, Department, 2015
This is a description of a teaching experience. You can use markdown like any other post.