mschrimpf/neural-nlp

[PNAS'21] The neural architecture of language: Integrative modeling converges on predictive processing

35
/ 100
Emerging

This project helps cognitive scientists and neuroscientists evaluate how well different computational language models predict human brain responses and behavior during language processing. You input a language model (like GPT-2) and a human neuroscience dataset, and it outputs a score indicating how closely the model's representations align with human brain activity or behavioral data. This is for researchers studying the neural basis of language.

No commits in the last 6 months.

Use this if you are a cognitive scientist or neuroscientist who wants to rigorously compare various computational language models against empirical human language processing data.

Not ideal if you are looking for a general-purpose natural language processing library for tasks like text generation or sentiment analysis.

cognitive-science neuroscience language-research brain-imaging computational-linguistics
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 19 / 25

How are scores calculated?

Stars

64

Forks

18

Language

Jupyter Notebook

License

Last pushed

Oct 25, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/mschrimpf/neural-nlp"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.