1860 Leroy Ave
Electrical Engineering and Computer Science
UC Berkeley
Berkeley, Ca 94720
(682) 564-6773
katie_stasaski@berkeley.edu

I'm an Applied Scientist at Salesforce Research. Previously, I earned my Ph.D. in computer science at the University of California, Berkeley, advised by Marti Hearst. My research lies at the intersection of natural language processing and education, and I am part of the Algorithms for Computing Education Lab. I'm thankful to be funded by the NSF Graduate Research Fellowships Program and a UC Berkeley Chancellor's Fellowship.

I'm broadly interested in questions around how NLP can improve the effectiveness of traditional education, make education more accessible, and improve the teaching process for teachers. I've recently worked on science question generation via an ontology and tutoring dialogue systems. I am additionally interested in making dialogue systems more diverse and personalizable to individual users.

I previously attended the George Washington University for my Bachelor's degree, where I was advised by Rahul Simha. I was in the Learning Technology Research Group and worked on a system which automatically generated reading questions and sent to a mobile applicaiton for illiterate adults learning to read.



Publications

Stasaski, K. and Hearst, M.A., Semantic Diversity in Dialogue with Natural Language Inference. To appear at NAACL 2022.

Stasaski, K., Rathod, M., Tu, T., Xiao, Y, and Hearst, M.A., Automatically Generating Cause-and-Effect Questions from Passages, BEA Workshop, EACL 2021.

Akalin, A, Weinman, N., Stasaski, K., and Fox, A., Exploring the Impact of Gender Bias on Pair Programming, ICER 2021.

Stasaski, K. and Ramanarayanan, V. Automatic Feedback Generation for Dialog-Based Language Tutors Using Transformer Models and Active Learning. Human-in-the-Loop Dialogue Systems Workshop at NeurIPS 2020.

Stasaski, K., Yang, G., and Hearst, M.A., More Diverse Dialogue Datasets via Diversity-Informed Data Collection, ACL 2020.

Stasaski, K., Kao, K., and Hearst, M.A., Construction of a Large Open Access Dialogue Dataset for Tutoring, BEA Workshop, ACL 2020.

Stasaski, K and Hearst, M.A., Multiple Choice Question Generation Utilizing an Ontology, BEA Workshop, EMNLP 2017.