About

I'm a computational linguist and NLP researcher currently in my 4th year of the Linguistics PhD program at Northwestern University, where I work with Rob Voigt in the Linguistic Mechanisms lab. My research uses machine learning and data science tools to generate actionable insights from large-scale data, including applications in information extraction, predictive modeling, and speech recognition. Currently, I'm working on my dissertation, where I'm using multimodal LLMs to explore how text and audio modalities contribute to how people express their commitment to their low-stakes opinions.

Selected Projects

LLM Selection: Improving ASR Transcript Quality via Zero-Shot Prompting
Vail Systems Intern Project (Summer 2024)

  • Developed a method for LLM-driven transcript selection of multi-ASR output
  • Achieved results approaching Oracle performance on company telephony datasets, significantly reducing Word Error Rates (WER) without ground truth supervision
  • Conference presentation: Real Time Communications Conference & Expo 2024 [talk slides]

Modeling Stance Investment in Low-Stakes Conversations Multimodally with Large Audio Language Models (LALMs)
Dissertation Project (2024-present)

  • Collecting a novel multimodal corpus to investigate speakers' commitments to their opinions
  • Comparing text-based and audio-based predictors of human conversational behavior
  • Evaluating multimodal LLMs' performance and alignment on novel conversational task

PLM-Augmented Rule-Based Classifiers: A Lightweight Method for Improving the Generalizability of Expert Knowledge in Novel Information Extraction Tasks
Masters Project (2022-2023)

  • Developed hybrid information extraction framework that combines expert knowledge (rule-based classifiers) with PLMs for improved generalizability
  • On task in educational domain, achieved 20% recall improvement over rule-based baseline with minimal precision loss
  • Conference presentation: Midwest Speech and Language Days 2024 [poster]

Skills

  • Programming Languages: Python, R
  • Libraries/Tools: Pytorch, NumPy, Pandas, spaCy, scikit-learn, matplotlib, nltk, Gensim
  • Other: Tableau, LaTeX

Education

Northwestern University (2021-present)

  • Ph.D. Linguistics (expected 2026)
  • M.A. Linguistics (2023)
  • Certificate in Cognitive Science

The Ohio State University (2017-2021)

  • B.A. Linguistics and Classics, summa cum laude
  • Minors: Computer Science, Statistics