Nupoor Gandhi (she/her)

I am a second-year Machine Learning and Public Policy PhD student at Carnegie Mellon University advised by Emma Strubell interested in structured representations of text from low-resource, policy-relevant domains. Currently, I am working with Yulia Tsvetkov and Alex Choulechova on building robust coreference resolution systems for child welfare data. Previously, I received my bachelors in Computer Science with a minor in Math at the University of Illinois at Urbana-Champaign. At Illinois I worked on modeling public health outcomes using social media data as a part of the Text Information Management and Analysis Group and the Health and Social Media Group working with ChengXiang Zhai and Dolores Albarracin. I was also a Data Science for Social Good Fellow at Imperial College London, where I worked on a QA system for nonprofit Barefoot Law to accelerate access to legal advice.  

Contact: nmgandhi(at)

Google Scholar | CV


Improving Span Representation for Domain-adapted Coreference Resolution. Gandhi, Nupoor, Anjalie Field, Yulia Tsvetkov. Proceedings of EMNLP 2021 Workshop on Computational Models of Reference, Anaphora and Coreference

Predicting Opioid Overdose Crude Rates with Text-Based Twitter Features (Student Abstract). Gandhi, Nupoor, Alex Morales, Sally Man-Pui Chan, Dolores Albarracin, and ChengXiang Zhai. Proceedings of the AAAI 2020.

Multi-Attribute Topic Feature Construction for Social Media-based Prediction. Morales, Alex, Nupoor Gandhi, Man-pui Sally Chan, Sophie Lohmann, Travis Sanchez, Kathleen A. Brady, Lyle Ungar, Dolores Albarracín, and ChengXiang Zhai. Proceedings of IEEE Big Data 2018