Scholar
Charles Lovering
Google Scholar ID: w0hYPqEAAAAJ
Kensho Technologies, Brown University
Citations & Impact
Citations
2,565
H-index
10
i10-index
11
Publications
20
Co-authors
0
Contact
Publications
Resume (English only)
Academic Achievements
- Publications:
- - Charles Lovering*, Jessica Forde*, George Konidaris, Ellie Pavlick, Michael Littman. Evaluation beyond Task Performance: Analyzing Concepts in AlphaZero in Hex. Neurips, 2022. (*Equal contribution.)
- - Charles Lovering, Ellie Pavlick. Unit Testing for Concepts in Neural Networks. TACL, 2022.
- - Charles Lovering, Rohan Jha, Tal Linzen, Ellie Pavlick. Predicting Inductive Biases of Pre-Trained Models. ICLR, 2021.
- - Rohan Jha, Charles Lovering, Ellie Pavlick. Does Data Augmentation Improve Generalization in NLP? 2020. PREPRINT.
Research Experience
- Work Experience:
- - Presented at Jane Street Research Symposium
- - Spoke at NLP & Fairness, Interpretability, and Robustness; Google
- - Gave talks at Language Understanding and Representations; Brown University
- - Worked on projects involving concept analysis in AlphaZero for Hex, unit testing for concepts in neural networks, predicting inductive biases of pre-trained models, etc.
Education
- Degree: PhD in Computer Science
- School: Not explicitly mentioned
- Advisor: Not explicitly mentioned
- Time: Not provided
- Field: Natural Language Understanding
Background
- PhD Student in Computer Science (NLU).
Miscellany
- Interests and Hobbies:
- - Creating Lindenmayer systems
- - Developing interactive visualizations
- - Writing introductions to byte-encoding representations, beam search, transformer architecture, and neural turing machines.
- Other:
- - This site replicates the distill design.
- - Uses Adobe XD CC for diagrams, D3 for visualizations, and PyTorch for deep learning.
Co-authors