NAACL 2022: Does Summary Evaluation Survive Translation?


Interested in reusing summarization resources in other languages, we investigated whether summary evaluations remain valid after applying machine translation to a dataset. Our findings were published in the Proceedings of the NAACL 2022 conference.

Socratic Models - AI Ensembles


As language models and multimodal models become more powerful, domain-specific finetuning may no longer be the dominant approach to powering AI applications. I looked into the growing literature on AI ensembles and built a Streamlit demo of these approaches to understand their abilities and failure modes.

Demand Forecasting with Bayesian Methods


Predicting blood platelet demand using online and GP regression

Selectively Editable Language Models


Experiments in editing large, pretrained language models using meta-learning techniques

Chinese Word Segmentation: Classic and Modern Methods


Working through a common NLP benchmark using classic ML and transformer-based methods

Unsupervised Text Style Transfer with Deep Learning


Exploration of deep learning architectures used for generative text style transfer