Human‑LLM Collaborative Annotation Through Effective Verification of LLM Labels
To appear at CHI 2024
Hello! I'm a Research Scientist at Megagon Labs working on human-centered AI. I received my Ph.D. from Georgia Tech where I worked with Haesun Park and Alex Endert.
My research aims to help people explore and interact with AI, focusing on improving interpretability, interactivity, and scalability, by designing and developing human-AI collaborative systems.
Recently, I'm working on human-LLM collaboration in various applications. If you are interested in similar topics, feel free to reach out!
Education
Aug 2015 - Dec 2020
Georgia Institute of Technology
Ph.D. in Computer Science
Aug 2013 - May 2015
Georgia Institute of Technology
M.S. in Computer Science (Machine Learning, GPA 4/4.0)
Mar 2011 - Aug 2013
Seoul National University
M.S. in Business Administration (Accounting)
Mar 2006 - Feb 2011
Seoul National University
B.S. in Mathematics (Minor in Business Administration)
Work Experience
Apr 2021 - Current
Megagon Labs
Research Scientist
May 2014 - Dec 2020
Georgia Institute of Technology
Graduate Research Assistant
May 2017 - Aug 2017
Disney Research
Research Intern
May 2016 - Aug 2016
IBM Research - Almaden
Research Intern
Publication
MEGAnno+: A Human-LLM Collaborative Annotation System
EACL 2024 Demo
Weedle: Composable Dashboard for Data-Centric NLP in Computational Notebooks
WWW 2023 Demo
Towards Transparent, Reusable, and Customizable Data Science in Computational Notebooks
CHI 2023 Late Breaking Work
MEGAnno: Exploratory Labeling for NLP in Computational Notebooks
EMNLP 2022 DaSH Workshop, Best Paper Award
Low-resource Interactive Active Labeling for Fine-tuning Language Models
EMNLP 2022 Findings
ArchiText: Interactive Hierarchical Topic Modeling
IEEE Transactions on Visualization and Computer Graphics (TVCG) 2020
TopicSifter: Interactive Search Space Reduction through Targeted Topic Modeling
IEEE Conference on Visual Analytics Science and Technology (VAST) 2019
Understanding Actors and Evaluating Personae with Gaussian Embeddings
AAAI 2019
VisIRR: An Interactive Visual System for Information Retrieval and Recommendation for Large-scale Document Data
TKDD 2017
High-Recall Document Retrieval from Large-Scale Noisy Documents via Visual Analytics based on Targeted Topic Modeling
IEEE Conference on Visual Analytics Science and Technology (VAST) 2017 Poster
PIVE: Per-Iteration Visualization Environment for Real-time Interactions with Dimension Reduction and Clustering
AAAI 2017
AxiSketcher: Interactive Nonlinear Axis Mapping through Users' Drawing on Visualization
IEEE Conference on Visual Analytics Science and Technology (VAST) 2016
Visualization by Demonstration: An Interaction Paradigm for Visual Data Exploration
IEEE Transactions on Visualization and Computer Graphics (TVCG) 2016
InterAxis: Steering Scatterplot Axes via Observation-Level Interaction
IEEE Conference on Visual Analytics Science and Technology (VAST) 2015
Simultaneous Discovery of Common and Discriminative Topics via Joint Nonnegative Matrix Factorization
KDD 2015
Doubly-Supervised Embedding Based on Label Information and Intrinsic Clusters for Visualization
Neurocomputing 2015
PIVE: Per-Iteration Visualization Environment for Supporting Real-time Interactions with Computational Methods
IEEE Conference on Visual Analytics Science and Technology (VAST) 2014 Poster, Best Poster Award
VisIRR: Visual Analytics for Information Retrieval and Recommendation for Large-Scale Document Data
IEEE Conference on Visual Analytics Science and Technology (VAST) 2014 Poster
Exploring Anomalies in GAStech: VAST Mini Challenge 1 and 2
IEEE Conference on Visual Analytics Science and Technology (VAST) 2014 VAST Challenge