Junmo Kang

Ph.D. Student, Georgia Tech

School of Interactive Computing

Coda 1147M

junmo.kang [AT] gatech.edu

About

I am a first-year Ph.D. student in the School of Interactive Computing at Georgia Tech co-advised by Prof. Alan Ritter and Prof. Wei Xu. I received my M.S. in Computer Science from KAIST, where I worked with Prof. Sung-Hyon Myaeng.

My primary research interests lie in the area of natural language processing (NLP) and machine learning (ML). The long-term goal of my research is to enhance the practicality of NLP systems (e.g., question answering) so that they can be widely used in real-world scenarios. In particular, my research focuses on i) how to make NLP models cheaper (i.e., efficient) in terms of data and computational resources, and ii) how to build NLP models that are robust to unseen cases in the wild. Here are some keywords:

News

Education

Georgia Institute of TechnologyAug. 2022 - Present

Ph.D. in Computer Science

Korea Advanced Institute of Science and Technology (KAIST)Feb. 2019 - Feb. 2021

M.S. in Computer Science

GPA: 4.03/4.3

Chungnam National UniversityMar. 2012 - Feb. 2019

B.E. in Computer Science & Engineering (Summa Cum Laude)

GPA: 4.3/4.5 (Rank: 1/125 in CSE, Major GPA: 4.41)

Publications

* indicates equal contribution.

Graph-Induced Transformers for Efficient Multi-Hop Question Answering

Giwon Hong, Jeonghwan Kim, Junmo Kang, Sung-Hyon Myaeng

In Proceedings of EMNLP, 2022.

Exploiting Numerical-Contextual Knowledge to Improve Numerical Reasoning in Question Answering

Jeonghwan Kim, Junmo Kang, Giwon Hong, Kyung-min Kim, Sung-Hyon Myaeng

In Proceedings of Findings of NAACL, 2022.

Ultra-High Dimensional Sparse Representations with Binarization for Efficient Text Retrieval

Kyoung-Rok Jang, Junmo Kang, Giwon Hong, Sung-Hyon Myaeng, Joohee Park, Taewon Yoon, Heecheol Seo

In Proceedings of EMNLP, 2021.

Leveraging Order-Free Tag Relations for Context-Aware Recommendation

Junmo Kang, Jeonghwan Kim, Suwon Shin, Sung-Hyon Myaeng

In Proceedings of EMNLP, 2021.

Have You Seen That Number? Investigating Extrapolation in Question Answering Models

Jeonghwan Kim, Giwon Hong, Kyung-min Kim, Junmo Kang, Sung-Hyon Myaeng

In Proceedings of EMNLP, 2021.

Can You Distinguish Truthful from Fake Reviews? User Analysis and Assistance Tool for Fake Review Detection

Jeonghwan Kim*, Junmo Kang*, Suwon Shin*, Sung-Hyon Myaeng

In Proceedings of HCI+NLP@EACL, 2021.

Regularization of Distinct Strategies for Unsupervised Question Generation

Junmo Kang*, Giwon Hong*, Haritz Puerto San Roman*, Sung-Hyon Myaeng

In Proceedings of Findings of EMNLP, 2020.

Handling Anomalies of Synthetic Questions in Unsupervised Question Answering

Giwon Hong*, Junmo Kang*, Doyeon Lim*, Sung-Hyon Myaeng

In Proceedings of COLING, 2020.

Let Me Know What to Ask: Interrogative-Word-Aware Question Generation

Junmo Kang*, Haritz Puerto San Roman*, Sung-Hyon Myaeng

In Proceedings of MRQA@EMNLP, 2019.

Vitæ

Full CV in PDF.

  • Georgia Tech Aug. 2022 - Present
    Ph.D. in Computer Science
  • KAIST IR&NLP Lab Mar. 2021 - July. 2022
    Research Associate
    Working on QA and IR
  • KAIST Feb. 2019 - Feb. 2021
    M.S. in Computer Science
    IR&NLP Lab
  • Poten Brothers Mar. 2017 - Feb. 2018
    Co-founder
    Startup
  • Republic of Korea Army Apr. 2013 - Jan. 2015
    Honorably discharged as Sergeant
    Compulsory military service
  • Chungnam National University Mar. 2012 - Feb. 2019
    B.E. in Computer Science & Engineering
    Summa Cum Laude