More about me 🚶

I grew up in Marietta, Georgia and now live a half-hour down in Midtown Atlanta where I'm currently in my final year at Georgia Tech. I thoroughly enjoy reading, hiking, apprasing knives and making homebrew nitrogen cold brew (and I'm an Eagle Scout!) ⛰️

I'm exploring the field of natural language processing with a focus on evaluation, modeling and deployment of constrained text generation models. 🤖

Publications & Preprints ✒️

Dancing Between Success and Failure: Edit-level Simplification Evaluation using SALSA 💃
David Heineman, Yao Dou, Mounica Maddela, Wei Xu
preprint, arXiv:2305.14458

LENS 🔎: A Learnable Evaluation Metric for Text Simplification
Mounica Maddela*, Yao Dou*, David Heineman, Wei Xu
ACL, 2023

* = equal contribution

What I've been working on 👷

• Under the PURA research award, working on diffusion models for natural language to create more robust generation (check out my new Huggingface decoding vizualizer extension). I'm currently advised by Prof. Wei Xu.
• Reading up on cognitive science and question answering! Here's some of my thoughts on evaluating reasoning in LLMs.
• Designed the first rate-and-rank human evaluation framework as co-author of the LENS project.

My past projects 🌳

• Earned 4th place in Georgia Tech's Wrek CTF (one of the largest greyhat hackathons in the south). See my answers here.
• Interned at AWS CloudWatch Application Insights, built infrastructure to monitor and group telemetry data from processes running on EC2 instances to identify the root causes of problems on customers' AWS infrastructure.
• Helped lead Georgia Tech's CS 3510, Design and Analysis of Algorithms as a teaching asssistant in Fall '21 and '22.
• Interned at Patientco (now part of Waystar), invented and deployed a new prediction model to predict when a patient pays their healthcare bill using their payment history.
• Voulenteered with the fake news detection team at Big Data Big Impact to create a scraper to increase 10x the volume of data which could be queried for real-time predictions.
• Deployed an efficient inference API to allow researchers to segment Twitter hashtags using a new segmentation model from Georgia Tech's NLP Lab.
• Developed a state-of-the-art method [code] for grading student essays using bi-directional LSTMs. (My work has been surpassed post-2020)