danqi/rc-cnn-dailymail

CNN/Daily Mail Reading Comprehension Task

40
/ 100
Emerging

This project helps researchers and natural language processing (NLP) engineers understand how well a computer can answer questions based on news articles. You input a document (like a CNN or Daily Mail article) and a question, and it outputs a predicted answer. This is primarily for those studying machine comprehension or developing question-answering systems.

292 stars. No commits in the last 6 months.

Use this if you are an NLP researcher or student working on improving machine reading comprehension models and need a baseline implementation for the CNN/Daily Mail dataset.

Not ideal if you need a plug-and-play application for general question-answering from arbitrary text, as this is a research implementation focused on a specific benchmark.

natural-language-processing machine-comprehension question-answering text-understanding academic-research
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 22 / 25

How are scores calculated?

Stars

292

Forks

56

Language

Python

License

Last pushed

Jan 25, 2017

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/danqi/rc-cnn-dailymail"

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