Ryan Cotterell
2 papers · Latest:
Natural Language Processing
Characterizing the Expressivity of Local Attention in Transformers
This paper formally explains why local attention improves Transformer quality by showing it adds expressive power, making hybrid models superior.
2605.00768
Natural Language ProcessingOn the Proper Treatment of Units in Surprisal Theory
This paper disentangles unit definition from tokenization in surprisal theory, proposing a unified framework for consistent linguistic analysis.
2604.28147
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.