Nupoor Gandhi (she/her)

I am a PhD student in Machine Learning and Public Policy at Carnegie Mellon University advised by Emma Strubell. I am interested in translational NLP, with emphasis on low-cost structured information extraction to meet the needs of researchers and practitioners in policy-relevant domains. 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.

I work on improving accessibility to rich, structured meaning representations of text in policy-relevant domains, with a particular focus on climate policy. Much of what governments commit to, let alone implement, is buried in long, dense, heterogeneous documents that are difficult to systemically analyze: My goal is to make climate policy legible and measurable at scale. To do this, I develop methods for efficiently structuring text under realistic resource constraints in settings that combine human expertise and language models.

More broadly, my research spans:

1. Structured representation as a more efficient way of doing document research.
2. Addressing failures to meet real-world complex information extraction needs.
3. The capacity of decomposition to reduce the cost of high quality annotation projects.

Contact: nmgandhi(at)cs.cmu.edu Google Scholar CV