umass-ml4ed/question-gen-aug-ranking

Official repo for "Improving Reading Comprehension Question Generation with Data Augmentation and Overgenerate-and-rank" (Outstanding paper at BEA@ACL 2023)

20
/ 100
Experimental

This project helps educators, content creators, and instructional designers automatically generate high-quality reading comprehension questions. You input a text passage and an answer, and it outputs a selection of well-formulated questions that test understanding. It's designed for anyone who needs to quickly create diverse and effective comprehension assessments, especially for complex texts.

No commits in the last 6 months.

Use this if you need to generate multiple, high-quality reading comprehension questions for a given text and its answer, and want to ensure they are diverse and effective.

Not ideal if you need to generate questions for very short, simple texts or if you require questions that go beyond standard reading comprehension (e.g., critical thinking, inference not tied to specific answers).

education-technology reading-comprehension assessment-creation curriculum-development e-learning
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 4 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

8

Forks

Language

Python

License

CC0-1.0

Last pushed

Dec 21, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/umass-ml4ed/question-gen-aug-ranking"

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