About Me
Hi! My name is Liam Dugan. I'm a 1st year Ph.D Student at University of Pennsylvania doing NLP research in the lab of Chris Callison-Burch.
For Summer 2022, I'll be heading to Roblox to work on Speech-to-Speech translation!
My current research deals with language modeling, human detection of generated text, machine translation, question generation, and sentence-level formality estimation.
My long term goal is to understand the implications and limitations of scale in large language mdoeling.
Feel free to look me up on Google Scholar or take my CV.
Recent News
[May 2022] | A Short Paper w/ collaborators at Google "The Case for a Single Model that can Both Generate Continuations and Fill in the Blank" was accepted to NAACL 2022 |
[Mar 2022] | My Short Paper "A Feasibility Study of Answer-Agnostic Question generation for education" was accepted to Findings of ACL 2022 |
[Jan 2022] | I gave a mini talk at Penn's weekly CLUNCH seminar on the detectability of human-machine text boundaries |
Recent Work
Watch the short presentation for my ACL 2022 paper and read the full document here!
Publications
The Case for a Single Model that can Both Generate Continuations and Fill in the Blank
Daphne Ippolito, Liam Dugan, Emily Reif, Ann Yuan, Andy Coenen, Chris Callison-Burch
NAACL 2022 (Short Papers)
A Feasibility Study of Answer-Agnostic Question Generation for Education
Liam Dugan, Eleni Miltsakaki, Shriyash Upadhyay, Etan Ginsberg, Hannah Gonzalez, Dayheon Choi, Chuning Yuan, Chris Callison-Burch
Findings of ACL 2022 (Short Papers)
Learning Formality from Japanese-English Parallel Corpora
Liam Dugan
Master's Thesis
RoFT: A Tool for Evaluating Human Detection of Machine Generated Text
Liam Dugan*, Daphne Ippolito*, Arun Kirubarajan*, Chris Callison-Burch
EMNLP 2020 (Demo Track)
Cloud Chaser: Real Time Deep Learning Computer Vision on Low Computing Power Devices
Zhengyi Luo, Austin Small, Liam Dugan, Stephen Lane
ICMV 2018
Blog