Minjoon Seo (서민준)

Research Scientist
NAVER Clova

PhD Candidate
Computer Science & Engineering
University of Washington
Office: CSE 386

seominjoon@gmail.com
[CV] [Google Scholar] [GitHub] [Twitter] [LinkedIn] [Bio]

Minjoon Seo, UW CSE

Broadly, I do research in natural language processing (NLP). More specifically, I am interested in question-driven learning models for extracting, accessing, and combining knowledge from natural language. I am advised by Hannaneh Hajishirzi, Ali Farhadi, and Oren Etzioni. I received BS in Electrical Engineering & Computer Science at UC Berkeley. Before coming to UW, I was a software engineer at Oracle.

Keywords: NLP, Machine Learning, AI, Deep Learning, Language & Vision


News

Jul 2018

We successfully finished the 1st Workshop on Machine Reading for Question Answering (MRQA) at ACL 2018. We look forward to see everyone again next year!

May 2017

I gave a talk at Microsoft Research.

Feb 2018

I am co-organizing a tutorial session "Standardized Tests as Benchmarks for AI" with Mrinmaya Sachan, Eric Xing, and Hannaneh Hajishirzi at EMNLP 2018. Details will be out soon; please consider attending!

Jan 2018

"Neural speed reading via Skim-RNN" is accepted to ICLR 2018. I also received Travel Award.

Jan 2018

I started working at NAVER Clova.

Oct 2017

I gave a talk at University of Southern California.

Sep 2017

I finished my summer internship (Jun - Sep) at the NLU Team of Google Research (NYC).


Publications

Refereed

  • Phrase-Indexed Question Answering: A New Challenge for Scalable Document Comprehension
    Minjoon Seo, Tom Kwiatkowski, Ankur P. Parikh, Ali Farhadi, Hannaneh Hajishirzi
    EMNLP 2018 (short)
    [paper]

  • Neural speed reading via Skim-RNN
    Minjoon Seo*, Sewon Min*, Ali Farhadi, Hannaneh Hajishirzi
    ICLR 2018
    [paper]

  • Zero-shot relation extraction via reading comprehension
    Omer Levy, Minjoon Seo, Eunsol Choi, Luke Zettlemoyer
    CoNLL 2017
    [paper] [website]

  • Question answering through transfer learning from large fine-grained supervision data
    Sewon Min, Minjoon Seo, Hannaneh Hajishirzi
    ACL 2017 (short)
    [paper]

  • Are you smarter than a sixth grader? Textbook question answering for multimodal machine comprehension
    Aniruddha Kembhavi, Minjoon Seo, Dustin Schwenk, Jonghyun Choi, Ali Farhadi, Hannaneh Hajishirzi
    CVPR 2017
    [paper]

  • Bidirectional attention flow for machine comprehension
    Minjoon Seo, Aniruddha Kembhavi, Ali Farhadi, Hannaneh Hajishirzi
    ICLR 2017
    [paper] [code] [website] [demo]

  • Query-reduction networks for question answering
    Minjoon Seo, Sewon Min, Ali Farhadi, Hannaneh Hajishirzi
    ICLR 2017
    [paper] [code]

  • A diagram is worth a dozen images
    Aniruddha Kembhavi, Mike Salvato*, Eric Kolve*, Minjoon Seo, Hannaneh Hajishirzi, Ali Farhadi
    ECCV 2016
    [paper] [dqa-net code]

  • Solving geometry problems: combining text and diagram interpretation
    Minjoon Seo, Hannaneh Hajishirzi, Ali Farhadi, Oren Etzioni, Clint Malcolm
    EMNLP 2015
    [paper] [code] [slides] [website] [demo]

  • BiliCam: using mobile phones to monitor newborn jaundice best paper nomination
    Lilian de Greef, Mayank Goel, Minjoon Seo, Eric Larson, James Stout, James Taylor, Shwetak Patel
    UbiComp 2014
    [paper] [website]

  • Diagram understanding in geometry questions
    Minjoon Seo, Hannaneh Hajishirzi, Ali Farhadi, Oren Etzioni
    AAAI 2014
    [paper] [code] [slides] [website]

* denotes equal contribution.

Personal

I enjoy bouldering, playing soccer and playing drum. I love trying out new restaurants with my wonderful fiancée.