Jinhyuk Lee

Visiting Postdoc, Princeton University

Postdoctoral Researcher, Korea University


I am a visiting postdoc at Princeton University advised by Prof. Danqi Chen and also a postdoctoral researcher at Korea University. My research area is based on natural language processing and deep learning. Specifically, I'm interested in learning generalizable text retrieval with dense vectors (i.e., dense retrieval) and tackling challenges in biomedical NLP. I was a PhD student at Korea University advised by Prof. Jaewoo Kang. During my PhD, I did an internship at NAVER Clova where I spent my time developing BioBERT and DenSPI.


2021.10 Check out our blog post on phrase retrieval!
2021.08 3 papers accepted to EMNLP 2021.
2021.05 1 paper (DensePhrases) accepted to ACL 2021.
2021.05 Gave a talk at Apple on learning dense phrase retrieval.
2021.02 Gave a talk at Google on learning dense phrase retrieval.

2020.09 2 papers (Position Bias, AdvSR-findings) accepted to EMNLP 2020.
2020.04 2 papers (Sparc, BioSyn) accepted to ACL 2020.
2020.03 Released covidAsk, a COVID-19 QA system (EMNLP NLP-COVID Workshop 2020).

2019.10 Gave a talk at KJDB 2019 and Tokyo Tech.
2019.09 Our team KU has won the seventh BioASQ challenge in 7b Phase B (Results)!
2019.08 1 paper (BioBERT) accepted to Bioinformatics.
2019.05 1 paper (DenSPI) accepted to ACL 2019.

Selected Publications

Phrase Retrieval Learns Passage Retrieval, Too
Jinhyuk Lee, Alexander Wettig, Danqi Chen
EMNLP 2021 (Long)
[Paper] [Code] [Demo]

Simple Entity-Centric Questions Challenge Dense Retrievers
Christopher Sciavolino*, Zexuan Zhong*, Jinhyuk Lee, Danqi Chen
EMNLP 2021 (short)
[Paper] [Code]

Can Language Models be Biomedical Knowledge Bases?
Mujeen Sung, Jinhyuk Lee, Sean Yi, Minji Jeon, Sungdong Kim, Jaewoo Kang
EMNLP 2021 (short)
[Paper] [Code]

Learning Dense Representations of Phrases at Scale
Jinhyuk Lee, Mujeen Sung, Jaewoo Kang, Danqi Chen
ACL 2021 (Long)
[Paper] [Code] [Demo]

Look at the First Sentence: Position Bias in Question Answering
Miyoung Ko, Jinhyuk Lee, Hyunjae Kim, Gangwoo Kim, Jaewoo Kang
EMNLP 2020 (Long)
[Paper] [Code]

Contextualized Sparse Representations for Real-Time Open-Domain Question Answering
Jinhyuk Lee, Minjoon Seo, Hannaneh Hajishirzi, Jaewoo Kang
ACL 2020 (Short)
[Paper] [Slide] [Code] [Demo]

Biomedical Entity Representations with Synonym Marginalization
Mujeen Sung, Hwisang Jeon, Jinhyuk Lee, Jaewoo Kang
ACL 2020 (Long)
[Paper] [Code]

Real-Time Open-Domain Question Answering on Wikipedia with Dense-Sparse Phrase Index
Minjoon Seo*, Jinhyuk Lee*, Tom Kwiatkowski, Ankur Parikh, Ali Farhadi, Hannaneh Hajishirzi
ACL 2019 (Long)
[Paper] [Code] [Demo]

BioBERT: a Pre-trained Biomedical Language Representation Model for Biomedical Text Mining
Jinhyuk Lee*, Wonjin Yoon*, Sungdong Kim, Donghyeon Kim, Sunkyu Kim, Chan Ho So, Jaewoo Kang
Bioinformatics (2019)
Applied to BERN (BioNER + Normalization), BioASQ models, etc
[Paper] [Code]

Ranking Paragraphs for Improving Answer Recall in Open-Domain Question Answering
Jinhyuk Lee, Seongjun Yun, Hyunjae Kim, Miyoung Ko, Jaewoo Kang
EMNLP 2018 (Short)
[Paper] [Code]

Name Nationality Classification with Recurrent Neural Networks
Jinhyuk Lee, Hyunjae Kim, Miyoung Ko, Donghee Choi, Jaehoon Choi, Jaewoo Kang
IJCAI 2017
[Paper] [Code]

Workshop Papers

Answering Questions on COVID-19 in Real-Time
Jinhyuk Lee, Sean S. Yi, Minbyul Jeong, Mujeen Sung, Wonjin Yoon, Yonghwa Choi, Miyoung Ko, Jaewoo Kang
NLP-COVID Workshop at EMNLP 2020
[Paper] [Code] [Web Service]

Pre-trained Language Models for Biomedical Question Answering
Wonjin Yoon, Jinhyuk Lee, Donghyeon Kim, Minbyul Jeong, Jaewoo Kang
BioASQ Workshop at ECML PKDD 2019
1st Place at the Seventh BioASQ Challenge (Task 7B) - Results
[Paper] [Code]

CollaboNet: Collaboration of Deep Neural Networks for Biomedical Named Entity Recognition
Wonjin Yoon*, Chan Ho So*, Jinhyuk Lee, Jaewoo Kang
DTMBIO Workshop at CIKM 2018 (Published in BMC Bioinformatics)
[Paper] [Code]