Education

• Master of Informatics, Graduate School of Informatics, Kyoto University (Apr. 2018-Mar. 2020, expected)
  • Major : Systems Science
  • Laboratory : Statistics and Machine Learning Lab.
  • Advisor : Prof. Hidetoshi Shimodaira
• Bachelor of Engineering, School of Informatics and Mathematical Science, Kyoto University (Apr. 2014-Mar. 2018)
  • Major : Applied Mathematics and Physics
  • Laboratory : Statistics and Machine Learning Lab.
  • Advisor : Prof. Hidetoshi Shimodaira

Publications & Presentations

Peer-reviewed International Conferences and Workshops

• J. Baek, G. Kim, J. Lee, S. Park, D. Han, S. Yun, S. J. Oh, and H. Lee. “What is wrong with scene text recognition model comparisons? dataset and model analysis”. arXiv preprint arXiv:1904.01906, 2019 (Accepted to ICCV) (Oral presentation).
  • Paper link
  • GitHub link
  • Acceptance rate (oral) : 4.3% (187/4303)
• G. Kim, A. Okuno, K. Fukui, and H. Shimodaira. “Representation Learning with Weighted Inner Product for Universal Approximation of General Similarities”. In Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence (IJCAI), 2019.
  • Paper link
  • Acceptance rate : 17.9% (850/4752)
• G. Kim, K. Fukui, and H. Shimodaira. “Segmentation-free Compositional n-gram Embedding”. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT), 2019.
  • Paper link
  • Acceptance rate (short) : 21.3% (142/666)
• A. Okuno, G. Kim, and H. Shimodaira. “Graph Embedding with Shifted Inner Product Similarity and Its Improved Approximation Capability”. In Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics (AISTATS), 2019.
  • Paper link
  • Aacceptance rate : 32.4% (360/1111)
• G. Kim, K. Fukui, and H. Shimodaira. “Word-like Character n-gram Embedding”. In Proceedings of the 2018 EMNLP Workshop W-NUT: The 4th Workshop on Noisy User-generated Text, 2018.
  • Paper link

Other Conferences and Workshops

• G. Kim, A. Okuno, and H. Shimodaira. “Embedding Words into Pseudo-Euclidean Space”. In Proceedings of the 25th Annual Meeting of the Association for Natural Language Processing (in Japanese), 2019.
  • Paper link
  • Selected to receive both awards: Young Researcher Award and Best Poster Award
• G. Kim, K. Fukui, T. Hada, and H. Shimodaira. “The acquisition of distributed representations of words via embedding word-like character n-gram”. In Proceedings of the 24th Annual Meeting of the Association for Natural Language Processing (in Japanese), 2018.
  • Paper link
• A. Okuno, G. Kim, and H. Shimodaira. “Representation Theorem of Graph Embedding with Neural Network and Its Extensions”. In The 21th Information-Based Induction Sciences Workshop (in Japanese), 2018.
• G. Kim, K. Fukui, T. Hada, and H. Shimodaira. “Segmentation-free Word Embedding with Word Dictionary”. In The 20th Information-Based Induction Sciences Workshop (in Japanese), 2017.

Research Experience

• Mathematical Statistics Team, RIKEN Center for Advanced Intelligence Project (Sep. 2017-Present)
  • As a research part-timer : Jul. 2017-Mar. 2018 and Jan. 2019-Present
  • As a trainee : Apr. 2018-Dec. 2018
  • Advisor : Prof. Hidetoshi Shimodaira
• Clova AI OCR Team, Clova AI Research, NAVER Corp. (2 months, Aug. 2018-Oct. 2018)
  • As a research intern
  • Advisor : Hwalsuk Lee
• Statistics and Machine Learning Lab., Kyoto University (Apr. 2017-Present)
  • Advisor : Prof. Hidetoshi Shimodaira

Selected Honors & Awards

• Young Researcher Award of the Twenty-fifth Annual Meeting of the Association for Natural Language Processing. 2019.
• Best Poster Award of the Twenty-fifth Annual Meeting of the Association for Natural LanguageProcessing. 2019.
• Seiwa International Students Scholarship. 2019.
• Korea-Japan Joint Government Scholarship. 2013–2018.
  • Admission and tuition fees, and living costs covered for a year of preliminary education and four years of Bachelor’s studies