Major research interests

Natural Language Processing, Dialogue System

Information Retrieval, Question Answering System

Text Mining, Text Classification/Summarization

Neural Symbolic AI, Multimodal System

Major research achievements (2021~present)

"Never Too Late to Learn: Regularizing Gender Bias in Coreference Resolution", International Conference on Web Search and Data Mining (WSDM), pp.15-23, Feb. 2023.

"QSG Transformer: Transformer with Query-Attentive Semantic Graph for Query-Focused Summarization", International ACM SIGIR Conference, pp. 2589-2594, July 2022.

"Lightweight Meta-Learning for Low-Resource Abstractive Summarization”, International ACM SIGIR Conference, pp. 2629-2633, July 2022.

"Query Reformulation for Descriptive Queries of Jargon Words Using a Knowledge Graph based on a Dictionary", International Conference on Information and Knowledge Management (CIKM), pp. 854-862, Nov. 2021.

"Self-supervised Fine-tuning for Efficient Passage Re-ranking”, International Conference on Information and Knowledge Management (CIKM), pp. 3142-3146, Nov. 2021.

"Self-Supervised Learning based on Sentiment Analysis with Word Weight Calculation",  International Conference on Information and Knowledge Management (CIKM), pp. 3428-3432, Nov. 2021.

"Using Topic Modeling and Adversarial Neural Networks for Fake News Video Detection", International Conference on Information and Knowledge Management (CIKM), pp. 2950-2954, Nov. 2021.

"Fine-grained Post-training for Improving Retrieval-based Dialogue Systems", Conference of the North American Chapter of the Association for Computational Linguistics (NAACL), pp. 1549-1558, June 2021.

“Graph-based Fake News Detection using a Summarization Technique”, European Chapter of the Association for Computational Linguistics (EACL), pp. 3276-3280, April 2021.

"Commonsense Knowledge Augmentation for Low-Resource Languages via Adversarial Learning”, AAAI Conference on Artificial Intelligence (AAAI), pp.6393-6401, Feb.2021.

주요 연구 분야 및 최근 3년간 실적

주요 연구 분야

Info Lab (In4Lab) is a part of the College of Computing, Sungkyunkwan University (SKKU), and members of the Lab are leading research activities in several areas of biomedical and information security.Our research work concentrates on computer security topics: user identification, authentication, hardening systems, malware, integrating AI for security tasks, robust machine learning, and adversarial machine learning. We are also actively engaged on several topics in biomedical research, including disease research, for a better understanding of the disease’s pathological causes and syndromes. Topics in biomedical research include brain neurodegenerative diseases detection and progression, intensive care unit, explainable deep learning and multi-modal architectures for biomedical problems, and GANs for medical images synthesis. The mission of the in4Lab is to progressively contribute to the fields of information security and biomedical fields through research and teaching.

현재 진행 중인 연구과제

As we collaborate widely with other researchers locally and globally to solve research problems related to information security and biomedical topics, we are also welcome new researchers and students interested in joining our team at In4Lab. Currently, we are engaged in the following funded projects.

- Intelligent and robust clinical decision support system for Alzheimer's disease.

- Artificial Intelligent-based skin analysis algorithms.

- Software authorship identification based on deep learning.

- Practical mobile continuous authentication

향후 전망

In4Lab research activities generally strengthen skills and knowledge related to data analysis, machine learning and deep learning modeling, statistical analysis, technical writing, and presentation. These skills are well-acknowledged by industry (companies) and academia. Prospective career path includes data science analyst, biomedical scientist, security professional, security scientist, forensic scientist, information security analyst.

필요 이수 과목 및 지식

- Since most of the research work at In4Lab requires programming skills to implement prototypes, solutions, or simulations, it is important to know well one or more programming languages (ex. Python, Java, C++/C languages)

- Computer security course is essential for security-related research.

- Fundamental knowledge about machine learning and deep learning are important for security and biomedical research