ReaLearn-Intern Workshop 2023
Introduction
The ReaLearn-Intern Workshop 2023 is held for the research presentations and discussions on the reasoning and learning for Trustworthy AI and the related areas. This workshop aims to create a networking platform for exchanging knowledge, exploring joint research opportunities, and cultivating partnerships that contribute to the advancement of AI research. It also offers an opportunity for internship students at ReaLearn to showcase their studies.
Participation is free, so please feel free to join us anytime. For preparation purposes, we would appreciate it if you could contact us in advance if you wish to attend. Of course, you are welcome to come on the day of the meeting without prior notice.
Information
Date: July 28 (Friday), 2023
Time: 13:00 - 14:50
Place: IS コラボ 7 / Collaboration Room 7
Speakers
Dr. Chaiyong Ragkhitwetsagul (Invited Speaker @ Faculty of ICT, Mahidol University, Thailand)
Mr. Nitit Ngamphotchanamongkol (Intern @ ReaLearn, JAIST)
Ms. Runchana Seesung (Intern @ ReaLearn, JAIST)
Mr. Siranut Akarawuthi (Intern @ ReaLearn, JAIST)
Speakers are provided with different time slots (including Q&A):
40 minutes for the invited speaker and
15 minutes for all the internship students.
Invited Speaker's Biography
Dr. Chaiyong Ragkhitwetsagul is a lecturer at the Faculty of Information and Communication Technology (ICT), Mahidol University, Thailand where he has co-founded the Software Engineering Research Unit (SERU). He received the PhD degree in Computer Science at University College London and was part of the Centre for Research on Evolution, Search, and Testing (CREST). His research interests include code search, code clone detection, software plagiarism, modern code review, and mining software repositories.
Schedule
(13:00 - 13:05) Opening speech by Dr. Teeradaj Racharak
(13:05 - 13:45) Dr. Chaiyong Ragkhitwetsagul
Title: Code Similarity and Its Applications (Slide: PDF)
Abstract: Code similarity is one of the fundamental concepts in software engineering. At the beginning, it was invented to find coding plagiarism and code clones, i.e., similar pieces of code in software. The definition of code similarity is open to decide by its application and the techniques that are employed to locate such similar code. One can look at the level of its sequence using text-based or token-based analysis, its structure by converting the code into abstract syntax tree, or its semantic by looking at its behaviors. Latest inventions in machine learning and deep learning also give rise to new ways to locate similar code. One can train machine learning models to detect similar pieces of code based on their features such as software metrics or sequencing of code tokens. Currently, there are many applications of code similarity in software engineering. It includes, but not limited to, locating code reuse from online sources, software license violations, recommending similar bug fixes, and recommending similar code reviews. In this talk, I will outline the concept of code similarity and discuss some state-of-the-art techniques in code similarity and its applications. I also will point out the gap in the current research and the future research directions in this area.
Chair: Dr. Teeradaj Racharak
=== 5-Minute Break =================
=== Internship Students' Session =====
== Chairs: Dr. Chaiyong, Dr. Teeradaj ==
(13:50 - 14:05) Mr. Nitit Ngamphotchanamongkol
Title: LLMs for Argumentation Mining from Text (Slide: PDF)
(14:05 - 14:20) Ms. Runchana Seesung
Title: Why are They Similar? Let's Explain via Description Logics (Slide: PDF)
(14:20 - 14:45) Mr. Siranut Akarawuthi
Title: Virtual Knowledge Graph with Explainable Similarity Reasoning (Slide: PDF)
===================================
(14:45 - 14:50) Closing speech by Dr. Chaiyong Ragkhitwetsagul