I am a predoctoral resident at The Allen Institute for Artificial Intelligence on the AllenNLP team, where I work with Matt Peters on controllable text generation and steering language models. I also collaborate with Margaret Mitchell on personal information in large web corpora. I am also an NLP researcher affiliated with Masakhane, an open source and distributed research effort for NLP for African languages.
Previously, I spent time in industry working on controlling language models, document understanding, optical character recognition, fake speech detection, and speech syntehsis at different companies in both an applied and research context. I completed my MS in Computer Science at the Courant Institute at NYU in the CILVR group focusing on deep learning applied to natural language processing and advised by Kyunghyun Cho and Sam Bowman. Before NYU, I completed my B.A. in Statistics and M.S. in Computer Science focusing on machine learning and natural language processing at Northwestern University working with Doug Downey.
Broadly, my research interests are:
I follow both international and club football (soccer), NBA basketball, and professional tennis very closely. I’m a huge supporter of Borussia Dortmund from the German Bundesliga.
Predoctoral Young Investigator at the Allen Institute for AI (AllenNLP team)
Predoctoral Resident at Intel’s Intelligent Systems Lab
ML Research Scientist at Scale AI
Research Scientist at AI Foundation
MS in Computer Science (Machine Learning) at New York University
Deep Learning Research Intern at Salesforce Research
Research Assistant in Deep Learning & NLP at Northwestern University
MS in Computer Science at Northwestern University
Master’s Exchange Student in Computer Science at ETH Zurich
Research Assistant in Biomedical Informatics at Stanford University
Research Assistant in Neural Network Language Modeling at Northwestern University
BA in Statistics at Northwestern University
We audit web-crawled multilingual datasets and find that many corpora are completely erroneus. Furthermore, we find that for many languages, less than 50% of sentences are of acceptable quality.
We introduce a living benchmark for natural language generation, its evaluation, and its metrics. This is the initial release of the benchmark for a shared task at our ACL 2021 workshop.
We look at how to condition GPT-2 to generate arbitrary sentences without fine-tuning and with simple optimization. Paves the way for research on universal decoders.
We create a dataset consisting of difficult natural images in order to evaluate robustness of object detection systems. We choose images that state-of-the-art models are confidently incorrect on. We find that although state-of-the-art models have improved on some benchmarks, they perform consistently terribly on this dataset.
We present a survey on deep learning approaches for optical character recognition and document understanding. We discuss methods for text detection, text transcription, document layout analysis, information extraction, and table understanding.
In this project, we focus on: 1) How can we build highly accurate, yet parameter and sample-efficient models for fake speech detection? 2) How can we rapidly adapt detection models to new sources of fake speech?
Project in which we looked at how to condition an unconditional recurrent neural network language model.
Novel methodology which enumerates the full set of causal graphs by converting any partial ancestral graph (PAG) to the set of all acyclic directed mixed graphs (ADMGs) that belong to the same Markov equivalence class encoded by the PAG.
Drop me an email if you are interested in collaborating on research or have any questions regarding my projects.