About me
PhD researcher in Computational Linguistics at UPenn with a B.S./M.Eng. in Electrical Engineering and Computer Science from MIT, specializing in deep learning and natural language processing (NLP). I have industry experience with patent-backed, client-facing explainable AI systems and NLP pipelines deployed to the U.S. Department of Defense, alongside a strong publication record and a proven track record of building scalable, production-ready Machine Learning (ML) systems.
My research bridges insights from human language acquisition and representation learning to develop data-efficient speech and language systems. I believe leveraing our human inductive biase toward spoken syllables may enable us drastically reduce the amount of input data needed to train speech models, thereby unlocking their capabilities for more linguistic communities around the world.
What I do
-
Natural Language Processing
Customized data analysis and natural language processing pipelines including OpenAI Assistant API integration.
-
LLM Benchmarking
In-depth linguistic evaluation of Large Language Models in comparison to traditional, statistical language models and human judgement data.
-
Linguistic Analysis
Application of multiple levels of linguistic analysis, including Pragmatics, Syntax, and Phonology; from different perspectives such as Theoretical, Historical, and Computational Linguistics.
-
Phonetics & DSP
Large scale digital signal processing (DSP) and acoustic analyses of speech databases to attest scientific hypotheses, answer theoretical questions or discover patterns in the data.
