• Publications
  • Influence
Is Attention Interpretable?
TLDR
While attention noisily predicts input components’ overall importance to a model, it is by no means a fail-safe indicator, and there are many ways in which this does not hold, where gradient-based rankings of attention weights better predict their effects than their magnitudes.
All That’s ‘Human’ Is Not Gold: Evaluating Human Evaluation of Generated Text
TLDR
The role untrained human evaluations play in NLG evaluation is examined and three approaches for quickly training evaluators to better identify GPT3-authored text are explored and it is found that while evaluation accuracy improved up to 55%, it did not significantly improve across the three domains.
Book Recommendation System
TLDR
This senior comprehensive project analyzed three systems that predict how users will rate specific books and created a system that makes these predictions based on data gathered from the Amazon Book Reviews dataset, BookCrossing dataset, GoogleBooks API, and GoodReads API.