Charles Lovering

Computer Science PhD Student (NLU).


Interesting stuff below ↓; a bit about me here ←.


Recent Work

  1. Charles Lovering, Rohan Jha, Tal Linzen, Ellie Pavlick. Predicting Inductive Biases of Pre-Trained Models. ICLR, 2021. Github.
  2. Rohan Jha, Charles Lovering, Ellie Pavlick. Does Data Augmentation Improve Generalization in NLP? 2020. PREPRINT.
  3. Charles Lovering, Ellie Pavlick. Self-play for Data Efficient Language Acquisition. 2020. PREPRINT.

Fun Visualizations

Unpublished Work


Talks (slides)

Methods (expositions)

Models (expositions)



This site replicates the distill design.

Adobe XD CC for diagrams, D3 for visualizations, and PyTorch for implementations (a plurality of the time).

If a diagram (or notes or presentation) proves useful, let me know (or cite this website)!