aviaefrat/cryptonite

The Official Repository of the Cryptonite Dataset

21
/ 100
Experimental

This dataset helps natural language processing (NLP) researchers evaluate how well their language models handle extreme linguistic ambiguity. It takes cryptic crossword clues as input and challenges models to find the correct answer, which often involves complex wordplay and hidden meanings. It's designed for NLP scientists and computational linguists pushing the boundaries of language understanding.

No commits in the last 6 months.

Use this if you are an NLP researcher developing or testing language models and need a robust benchmark for understanding highly ambiguous language.

Not ideal if you are looking for a dataset to solve standard crosswords or to train models on straightforward language understanding tasks.

natural-language-processing linguistic-ambiguity computational-linguistics language-model-evaluation text-analysis
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 7 / 25

How are scores calculated?

Stars

23

Forks

2

Language

Python

License

Last pushed

Feb 19, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/aviaefrat/cryptonite"

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