Hello! I'm Milind Agarwal and I'm a second-year Computer Science PhD student at George Mason University. I'm currently doing research in Scalable Data Extraction for Low-Resource Languages. For my PhD, this means that I am exploring research challenges in language identification and optical character recognition (OCR) for low-resource languages. I'm lucky to be advised by Prof. Antonis Anastasopoulos and be a part of GMU's NLP lab .
Before starting my PhD at Mason, I spent four years in Baltimore at Johns Hopkins University, where I completed my BS and MSE degrees in Computer Science. During my undergraduate years, I spent a few memorable summers interning with Prof. David Yarowsky , Prof. Janet Markle, and Prof. Alexis Battle, with whom I cultivated my interest in academic research.
News
- April 2024: I presented joint work with labmate Joshua Otten on "Script-Agnostic Language Identification" at the first SouthNLP symposium at Emory University!
- March 2024: Invited talk on "Language Identification" at Notre Dame University! The talk covered 3 of my papers on LangID.
- Dec 2023: I presented my work, LIMIT (hierarchical language identification), at EMNLP 2023's Main Conference in Singapore!
- Nov 2023: I passed my Qualifiers and the Comprehensive Exam! Onwards to the PhD Thesis Proposal
- April 2023: Our NLP group organized MTMA 2023 and MASC-SLL 2023 at George Mason!
- We're organizing the Dialectal and Low-resource Track at IWSLT, co-located with ACL 2023 in Toronto! Training data available in Tunisian Arabic, Irish, Marathi, Maltese, Pashto, Tamasheq, and Quechua (with translations into English, Hindi, French, Spanish)
- I was accepted to attend the CRA's Grad Cohort Workshop for Inclusion, Diversity, Equity, Accessibility, and Leadership Skills (IDEALS) in Honolulu, Hawaii!
Email: magarwa at gmu dot edu
Twitter: @milind_ag
GitHub: @magarw