she/her
I’m a second-year PhD student in Computer Science and Engineering at UC San Diego working with Professor Ndapa Nakashole.
My research centers on natural language processing, especially I’m focusing on weakly supervised learning and its interpretability, and joint learning methods for entity retrieval using autoregressive generation models. I’m also interested in knowledge graph representations and the use of graph-structured data for various NLP applications.
Prior to UCSD, I worked as a researcher in Natural Language Processing lab at Sungkyunkwan University with Prof. Youngjoong Ko. I received B.S. and M.S. in Computer Science and Engineering at Sogang University. After my undergraduate, I worked at Coupang as a software engineer.
Conference Proceedings
Data Augmentation for Rare Symptoms in Vaccine Side-Effect Detection. Bosung Kim and Ndapa Nakashole. 2022 (BioNLP 2022) [pdf] [code]
Query Reformulation for Descriptive Queries of Jargon Words Using a Knowledge Graph based on a Dictionary. Bosung Kim, Hyewon Choi, Haeun Yu, and Youngjoong Ko. 2021 (CIKM 2021) [link]
Commonsense Knowledge Augmentation for Low-Resource Languages via Adversarial Learning. Bosung Kim*, Juae Kim*, Youngjoong Ko, and Jungyun Seo. 2020. (AAAI 2021) (*Equal contribution) [link] [code]
Multi-task learning for Knowledge Graph Completion using Pre-trained Language. Bosung Kim, Taesuk Hong, Youngjoong Ko, and Jungyun Seo. 2020 (COLING 2020) [pdf] [code]
Journal Articles