Named to Forbes 30 Under 30 in Science for her work on NLP for endangered languages.
Led multiple research projects including OCR-EL (OCR for endangered languages), temporally-aware NER, low-resource entity extraction and linking, and OCR models to identify printers of historical documents like John Milton’s Areopagitica.
Published numerous papers in top-tier venues such as TACL, EMNLP, ACL, and CoNLL, including 'OCR Post-Correction for Endangered Language Texts' and 'Soft Gazetteers for Low-Resource Named Entity Recognition'.
Organized academic workshops including the Workshop on Computational Methods for Endangered Languages at ICLDC 2023 and ACL 2022, and the Student Research Workshop at ACL 2020.
Served as Area Chair for the Multilinguality track at EMNLP 2022 and as a reviewer for major conferences including ACL, EMNLP, AAAI, and NAACL.