What do I do?
I am generally interested in how we can represent meaning in ways that are both useful and illuminating. My thesis work focused on using explicit semantic representations to make neural language models interpretabile and controllable. I have also worked on the Columbia SAFE Lab’s gang violence prevention project as well as on analyzing therapeutic conversation.
Publications
2023
Narutatsu Ri, Fei-Tzin Lee, Nakul Verma. Contrastive Loss is All You Need to Recover Analogies as Parallel Lines (accepted to Repl4NLP 2023).
2022
Fei-Tzin Lee, Miguel Ballesteros, Feng Nan, Kathleen McKeown. Using Structured Content Plans for Fine-grained Syntactic Control in Pretrained Language Model Generation.
2021
Fei-Tzin Lee, Chris Kedzie, Nakul Verma, Kathleen McKeown. An analysis of document graph construction methods for AMR summarization (preprint).
2020
Desmond Patton, William Frey, Kyle McGregor, Fei-Tzin Lee, Kathleen McKeown, Emanuel Moss. Contextual Analysis of Social Media: The Promise and Challenge of Eliciting Context in Social Media Posts with Natural Language Processing.
2019
Fei-Tzin Lee, Derrick Hull, Jacob Levine, Bonnie Ray, and Kathleen McKeown. Identifying therapist conversational actions across diverse psychotherapeutic approaches.
Philipp Blandfort, Desmond Patton, William Frey, Svebor Karaman, Surabhi Bhargava, Fei-Tzin Lee, Siddharth Varia, Chris Kedzie, Michael Gaskell, Rossano Schifanella, Kathleen McKeown, and Shih-Fu Chang. Multimodal Social Media Analysis for Gang Violence Prevention.
2018
Serina Chang, Ruiqi Zhong, Ethan Adams, Fei-Tzin Lee, Siddharth Varia, Desmond Patton, William Frey, Chris Kedzie, and Kathleen McKeown. Detecting Gang-Involved Escalation on Social Media Using Context.