EduNLP Lab
The EduNLP Lab is an interdisciplinary group of researchers and students working with Dr. Dora Demszky
We use Natural Language Processing (NLP) technology to empower teachers and students.
Human connections come first.
We leverage technology to support, sustain and improve the human connections key to teaching and learning. We want educators to become the best educators they can be, to continuously improve, and to create transformative learning opportunities for all students.
Our work is at the cross section of education, computer science and linguistics. We are uniquely positioned to gather evidence, develop algorithms and pilot solutions.
Gather Evidence
We surface what works in learning environments with data science using NLP models.
We work to understand ways in which technology can be effective at facilitating better human interaction, better teaching and better student outcomes.
Develop Algorithms
We construct frameworks for understanding data through co-design. We partner with domain experts to validate algorithms based on representative data samples then apply these measurement tools to our larger data sets to gain research insights.
Pilot Solutions
We implement these validated algorithms in tools that practitioners can use. These R&D tools support teachers to use research-based strategies and allow us to run tests and learn about how technologies can support human interaction and student success.
We are making contributions across these three areas in multiple projects and partnerships.
EduNLP Lab in the Media
-
Language Models in the Classroom: Bridging the Gap Between Technology and Teaching
Instructors and students from Stanford class CS293/EDUC473 address the failures of current educational technologies and outline how to empower both teachers and learners through co -
Stanford GSE course tackles gap between edtech research and real-world practice
Taught by Assistant Professor Dora Demszky, Empowering Educators via Language Technology aims to connect edtech creators and teachers to create better learning tools. -
AI Helps Math Teachers Build Better "Scaffolds"
Education researchers have evaluated the ability of large language models (LLMs) to help middle school math teachers structure tiered lessons to reach diverse skill levels.
Upcoming Opportunities
-
Conference / Symposium
Practitioner Voices: Language Technologies in Math Education
Free summit for math teachers and leaders June 23-24, 2025Bringing together practitioners to help shape the future of language technologies in math education.-Stanford University
Stanford, CA 94305
United States