I majored in natural language processing, which enables artificial intelligence to understand and reponse to human speech. Specifically, I have studied and developed language understanding, data augmentation methods, question-answering systems and large-scale language models. My future research aims to address ethical issues inherent in text data and language models to create the ultimate artificial intelligence.

저는 인공지능이 사람의 말을 이해하고 응답 할 수 있게 하는 자연어처리를 전공했습니다. 특히, 언어이해 기술, 데이터 확장 방법, 질의 응답 시스템과 거대 언어모델을 활용하는 방법을 연구/개발 해왔습니다. 앞으로는 궁극적인 인공지능을 만들기 위해 텍스트와 언어모델에 포함된 윤리적 문제를 극복하는 연구도 진행할 예정입니다.

최종학력

Ph.D. in Computer Science, Sogang University

전공분야

Natural Language Processing

주요 연구

• Machine Learning for Natural Language Processing
• Semi-supervised Learning
• Question Answering System

주요 강의

• Programming
• Natural Language Processing

주요 논문/저서

(International Journal)

• Juae Kim, Yejin Kim, Sangwoo Kang, Jungyun Seo. (2022). Weakly Labeled Data Augmentation for Social Media Named Entity Recognition. Expert systems with applications. (SCI – Q1) (IF: 8.665) 
  
  
• Juae Kim, Yejin Kim, Sangwoo Kang. (2021). Adaptive Named Entity Recognition Using Distant Supervision for Contemporary Written Texts. IEEE Access, 9, 80405-80414 (SCIE) (IF: 3.367)
  
  
• Juae Kim, Youngjoong Ko, Jungyun Seo. (2020). Construction of Machine-Labeled Data for Improving Named Entity Recognition by Transfer Learning. IEEE Access, 8, 59684-59693. (SCIE) (IF: 3.367)
  
  
• Juae Kim, Youngjoong Ko, Jungyun Seo. (2019). A Bootstrapping Approach with CRF and Deep Learning Models for Improving the Biomedical Named Entity Recognition in Multi-domains. IEEE Access, 7, 70308-70318, (SCIE) (IF: 3.367)
  
  

(International Conference)

• Minwoo Lee, Seungpil Won, Juae Kim, Hwanhee Lee, Cheoneum Park, Kyomin Jung. (2021). CrossAug: A Contrastive Data Augmentation Method for Debiasing Fact Verification Models. Proceedings of CIKM 2021. 
  
  
• *Bosung Kim, Juae Kim (co-first author), Youngjoong Ko, Jungyun Seo (2021). Commonsense Knowledge Augmentation for Low-Resource Languages via Adversarial Learning. Proceedings of AAAI-2021. 
  
  
• *Yejin Kim, Juae Kim (co-first author), Jungyun Seo. (2020). Noise Improves Noise: Verification of Pre-training Effect with Weakly Labeled Data on Social Media NER. Proceedings of the Big Data and Smart Computing (BigComp), Busan, Korea.
  
  
• *Cheoneum Park, Juae Kim (co-first author), Hyeon-gu Lee, Reinald Kim Amplayo, Harksoo Kim, Jungyun Seo, Changki Lee. (2019). ThisIsCompetition at SemEval-2019 Task 9:BERT is unstable for out-of-domain samples. Proceedings of the 13th International Workshop on Semantic Evaluation (SemEval-2019), Minneapolis, USA. 
  
  
• Juae Kim, Youngjoong Ko , Jungyun Seo. (2019). Transfer Learning from Automatically Annotated Data for Recognizing Named Entities in Recent Generated Texts. Proceedings of the Big Data and Smart Computing (BigComp) 2019, Kyoto, Japan. 
  
  
• Hwijeen Ahn, Minyoung Seo, Chanmin Park, Juae Kim , Jungyun Seo. (2019). Extensive Use of Morpheme Featrues in Korean Dependency Parsing. Proceedings of the Big Data and Smart Computing (BigComp) 2019, Kyoto, Japan. 
  
  
• Juae Kim, Soonjae Kwon, Youngjoong Ko , Jungyun Seo. (2017). A Method to Generate a Machine-labeled Data for Biomedical Named Entity Recognition with Various Sub-Domains. Proceedings of International Workshop on Digital Disease Detection Using Social Media (IJCNLP 2017), Taiwan. 
  
  
• Hyeon-gu Lee, Minkyung Kim, Harksoo Kim, Juae Kim, Sunjae Kwon, Jungyun Seo, Jungkyu Choi, Yi-reun Kim. (2016). KSAnswer: Question-answering System of Kangwon National University and Sogang University in the 2016 BioASQ Challenge. Proceedings of the BioASQ Challenge Workshop, Berlin, Germany.