Dora Demszky

Google Scholar | Github | LinkedIn | CV

Hi there! I'm a PhD candidate in the Linguistics Department at Stanford University, advised by Dan Jurafsky. I'm a member of the Stanford NLP group. I publish under my full name, Dorottya Demszky.

My research focuses on building and deploying natural language processing methods to support equitable and student centered education. I combine machine learning with linguistic theory and input from practitioners to develop interpretable and scalable education measures. By deploying these measures, I aim to improve educational interventions, teachers' professional development and the equity of curricular materials.

I am invested in understanding how NLP can be put to the service of social good. I primarily focus on solving problems in education, but in the past I also worked on dialect feature recognition, emotion detection, and on using natural language processing to understand political issues, such as polarization and propaganda.

I am grateful to my incredible collaborators, mentors and mentees, who have made our projects possible and have made me a better person and researcher.

You can reach me at ddemszky [at] stanford [dot] edu.

News

Publications
Measuring Conversational Uptake: A Case Study on Student-Teacher Interactions
Dorottya Demszky, Jing Liu, Zid Mancenido, Julie Cohen, Heather Hill, Dan Jurafsky & Tatsunori Hashimoto
ACL (2021)

Learning to Recognize Dialect Features
Dorottya Demszky, Devyani Sharma, Jonathan H. Clark, Vinodkumar Prabhakaran & Jacob Eisenstein
NAACL (2021)

Content Analysis of Textbooks via Natural Language Processing: Novel Findings on Gender, Race, and Ethnicity in Texas US History Textbooks
Li Lucy*, Dorottya Demszky*, Patricia Bromley, & Dan Jurafsky *equal contribution
American Education Research Association (AERA) Open Journal (2020)
2020 Education Data Science Conference Best Paper Award
[slides] [code] [Stanford HAI article]

GoEmotions: A Dataset of Fine-Grained Emotions
Dorottya Demszky, Dana Movshovitz-Attias, Jeongwoo Ko, Alan Cowen, Gaurav Nemade & Sujith Ravi
ACL 2020
[slides] [code & data] [t-SNE plot]

The Role of Verb Semantics in Hungarian Verb-Object Order
Dorottya Demszky, László Kálmán, Dan Jurafsky, & Beth Levin
Proceedings of the Linguistic Society of America
[LSA 2021 slides] [flowchart] [supplementary material]

Pártélet: A Hungarian Corpus of Propaganda Texts from the Hungarian Socialist Era
Zoltán Kmetty, Veronika Vincze, Dorottya Demszky, Orsolya Ring, Balázs Nagy & Martina Katalin Szabó
LREC 2020

Analyzing Polarization in Social Media: Method and Application to Tweets on 21 Mass Shootings
Dorottya Demszky, Nikhil Garg, Rob Voigt, James Zou, Jesse Shapiro, Matthew Gentzkow & Dan Jurafsky
ACL 2019
[code and data] [NAACL slides] [Stanford News, Washington Post]

Transforming Question Answering Datasets Into Natural Language Inference Datasets
Dorottya Demszky*, Kelvin Guu* & Percy Liang *equal contribution
arXiv preprint arXiv:1809.02922.
[code] [data]
Internships
In the summers of 2019 and 2020, I was a Research Intern at Google, where I got the chance to work on great teams on NLP projects.
Other Activities
In 2016, I co-founded a nonprofit organization, Tarisznya Alapítvány (Knapsack Foundation), the goal of which is to empower underprivileged children in Hungary through education. You can learn more on our website or on Facebook.
Mentors & Mentees

Academic Mentors*: Patricia Bromley (Stanford University), Jon Clark (Google Research), Jacob Eisenstein (Google Research), Christiane Fellbaum (Princeton University), Adrienne Fráter (Városmajori Gimnázium), Nikhil Garg (Cornell Tech), Matthew Gentzkow (Stanford University), Kelvin Guu (Google Research), Tatsu Hashimoto (Stanford University), Heather Hill (Harvard University), Dan Jurafsky (Stanford University), László Kálmán (ELTE), Joshua Katz (Princeton University), Jeongwoo Ko (Google Research), Erika Kovács (Városmajori Gimnázium), Júlia Lázár (Városmajori Gimnázium), Beth Levin (Stanford University), Percy Liang (Stanford University), Jing Liu (University of Maryland), Dana Movshovitz-Attias (Google Research), Chris Piech (Stanford University), Vinod Prabhakaran (Google AI Ethics), Jesse Shapiro (Brown University), Devyani Sharma (Queen Mary, University of London), Rob Voigt (Northwestern University)
*not an exhaustive list

Current and Former Research Mentees:

  • Audrey Acken (High school student)
  • Sterling Alic (Co-term student @ Stanford)
  • Elizabeth Fitzgerald (Undergraduate @ Stanford)
  • Grace Hu (Undergraduate @ Stanford)
  • Lucy Li (PhD student @ UC Berkeley; formerly Co-term student @ Stanford)