🤓 About
I am a Ph.D. candidate in Computer Science at the University of Maryland working with Prof. Hal Daumé III. I am a member of the CLIP Lab.
My research interests involve moving towards trustworthy and fair natural language processing systems. Currently, I am working on analyzing how stereotypes manifest in large pretrained language models. I am also working on human-centered NLP and VQA for Blind people.
Previously, I obtained my Bachelor's degree in Computer Science from Bryn Mawr College and Mathematics from Haverford College.
📰 Recent News
| July 2023 | Co-organized the 3nd TrustNLP Workshop at ACL 2023. |
| July 2022 | Co-organized the 2nd TrustNLP Workshop at NAACL 2022. |
| November 2021 | Co-mentored students in Tech + Research 2021: Welcoming Women to Computing Research. |
| May - August 2021 | Interned at Amazon Alexa Research, working with Rahul Gupta and Kai-Wei Chang. |
📜 Publications
What's Different between Visual Question Answering for Machine ``Understanding'' Versus for Accessibility?
Yang Trista Cao*, Kyle Seelman*, Kyungjun Lee*, Hal Daumé III
AACL IJCNLP 2022
Best Theme Paper Award
On the intrinsic and extrinsic fairness evaluation metrics for contextualized language representations
Yang Trista Cao*, Yada Pruksachatkun*, Kai-Wei Chang, Rahul Gupta, Varun Kumar, Jwala Dhamala, Aram Galstyan
ACL 2022 (Short Paper)
Theory-Grounded Measurement of US Social Stereotypes in English Language Models
Yang Trista Cao*, Anna Sotnikova*, Hal Daumé III, Rachel Rudinger, Linda Zou
NAACL 2022 (Oral)
Analyzing Stereotypes in Generative Text Inference Tasks
Anna Sotnikova*, Yang Trista Cao*, Hal Daumé III, Rachel Rudinger
ACL-IJCNLP 2021 (Findings)
Toward Gender-Inclusive Coreference Resolution: An Analysis of Gender and Bias throughout the Machine Learning Lifecyle
Yang Trista Cao, Hal Daumé III
Computational Linguistics. 47 (3)
Toward Gender-Inclusive Coreference Resolution
Yang Trista Cao, Hal Daumé III
ACL 2020
[GitHub]
Controlling the Specificity of Clarification Question Generation
Yang Trista Cao, Sudha Rao, Hal Daumé III
Widening NLP 2019