About

Photo credit: Anna Wu Photography

Mina Lee
minalee@stanford.edu

I am a final year Ph.D. candidate in Computer Science at Stanford University advised by Professor Percy Liang.

Language Models  ·   Human-AI Interaction  ·  NLP  ·   HCI

News


Research Interests

I strive to enhance our productivity and creativity in the writing process by leveraging language models (LMs). Concretely, I evaluate LMs based on their ability to interact with humans and build LMs to augment human capabilities. From helping users type sentences faster, to inspiring writers to come up with something creative, to helping programmers write code more easily, I am interested in the interaction between humans and machines and how technology can aid humans to be better writers.

My research is in natural language processing (NLP) and draws inspiration from human-computer interaction (HCI). I publish in both NLP and HCI conferences (e.g., ACL, NAACL, and CHI).


Stanford Natural Language Processing Group
Stanford Artificial Intelligence Lab
Stanford Center for Research on Foundation Models
Stanford Institute for Human-Centered Artificial Intelligence


Education

Stanford University, Stanford, CA, USA (2017 – Present)
Ph.D. Candidate in Computer Science

Korea University, Seoul, Republic of Korea (2016)
Bachelor of Science in Computer Science and Engineering

University of British Columbia, Vancouver, BC, Canada (2015)
Exchange Student


Publications

Evaluating Human-Language Model Interaction
Mina Lee, Megha Srivastava, Amelia Hardy, Esin Durmus, Ashwin Paranjape, John Tickstun, Ines Gerard-Ursin, Faisal Ladhak, Frieda Rong, Rose E. Wang, Lisa Li, Minae Kwon, Joon Sung Park, Hancheng Cao, Tony Lee, Rishi Bommasani, Michael Bernstein, Percy Liang
In preparation

TempLM: Distilling Language Models into Template-Based Generators
Tianyi Zhang, Mina Lee*, Lisa Li*, Ende Shen*, Tatsunori Hashimoto
Preprint

[paper] [code]

CoAuthor: Designing a Human-AI Collaborative Writing Dataset
for Exploring Language Model Capabilities
Mina Lee, Percy Liang, Qian Yang
CHI 2022
Honorable Mention Award 🏆

[paper] [website] [slides] [talk] [certificate]
[article by Stanford HAI] [article by The Economist]

On the Opportunities and Risks of Foundation Models
§2.5 Interaction: Joon Sung Park, Chris Donahue, Mina Lee, Siddharth Karamcheti, Dorsa Sadigh, Michael Bernstein
§5.5 Economics: Zanele Munyikwa, Mina Lee, Erik Brynjolfsson
Preprint

[paper]

Swords ⚔️: A Benchmark for Lexical Substitution
with Improved Data Coverage and Quality
Mina Lee*, Chris Donahue*, Robin Jia, Alexander Iyabor, Percy Liang
NAACL 2021

[paper] [code] [codalab]

Enabling Language Models to Fill in the Blanks
Chris Donahue, Mina Lee, Percy Liang
ACL 2020

[paper] [code] [demo] [blog] [slides] [talk]

Learning Autocomplete Systems as a Communication Game
Mina Lee, Tatsunori Hashimoto, Percy Liang
NeurIPS 2019 Workshop on Emergent Communication
Selected for Contributed Talk

[paper] [code] [poster] [slides] [talk]

SPoC: Search-based Pseudocode to Code
Sumith Kulal, Panupong Pasupat, Kartik Chandra, Mina Lee, Oded Padon, Alex Aiken, Percy Liang
NeurIPS 2019

[paper] [website]

Synthesizing Regular Expressions from Examples
for Introductory Automata Assignments
Mina Lee*, Sunbeom So*, Hakjoo Oh
GPCE 2016
Best Paper Award 🏆

[paper] [code] [poster] [blog]


Teaching Experience

CS49 Foundations of Computer Programming at Foothill College (2022) – Shadow Professor Eric Reed through the Preparing Future Professors program

CS224N Natural Language Processing with Deep Learning at Stanford University (2020) – Assist Professor Chris Manning as a Course Assistant


CPSC261 Basics of Computer Systems at University of British Columbia (2015) – Assist Professor Patrice Belleville as a Teaching Assistant


Industry Experience

Meta (formerly Facebook), Menlo Park, CA, USA (2018)
Software Engineer Intern

minalee_nccs_facebook.jpg
Neural Contextual Code Search: Search Engine for PyTorch Functions

Trap Danmark, Copenhagen, Denmark (2015)
Software Engineer Intern


Workshop

Organizer for Intelligent and Interactive Writing Assistants at ACL 2022


Program committee for CtrlGen Workshop at NeurIPS 2021


Media Coverage

MIT Technology Review Korea Announces Korean Winners of “Innovators Under 35” by MIT Technology Review (November 2022)

Searching for the “Second Zuckerberg” That Will Shake the World by Maeil Business Newspaper (November 2022)

[IU 35 Korea] Mina Lee (Stanford University)—AI Language Model by ETNews (November 2022)

Could AI Help You to Write Your Next Paper? by Nature (October 2022)

AI Writing Assistants: A Cure for Writer’s Block or Modern-Day Clippy? by PCMag (September 2022)

Huge “Foundation Models” are Turbo-charging AI Progress by The Economist (June 2022)

He Writes His Next Screenplay with an AI and the Result Fascinates Him by LADN (June 2022)

Meet CoAuthor, an Experiment in Human-AI Collaborative Writing by Stanford Human-Centered Artificial Intelligence (May 2022)

Written by AI? Can AI Really Write? by KT DX Insight (January 2022)

At Stanford, Supportive Group Culture Leads to Increased Learning Opportunities by AI Times (May 2021)

Stanford School of Engineering Spotlights: Mina Lee by Stanford School of Engineering (July 2018)

Book

지금 알려줄게요, 미국대학원 (2017)