# patil-suraj/question_generation

Neural question generation using transformers

Repository: https://github.com/patil-suraj/question_generation
Canonical: https://ross.abutalabs.com/products/question_generation
Language: Jupyter Notebook
License: MIT
License Family: permissive
Topics: nlp, nlg, deep-learning, transformer, t5, question-generation, natural-language-processing, natural-language-generation
Last push: 2024-04-05T13:52:05+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2252, "days_push": 880, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1141, forks 347 (observed 2026-08-28T04:03:44.663076+00:00)

## What it is
An open-source study and library for neural question generation using pre-trained seq2seq transformer models like T5 via Hugging Face transformers. It provides pipelines for answer-aware, multitask QA-QG, and end-to-end answer-agnostic question generation, plus simplified training and evaluation scripts.

## Use cases
- generate questions from a text passage
- create quiz questions from articles automatically
- generate questions for a given answer and context
- build QA datasets by generating questions from documents
- fine-tune a transformer model for question generation
- extract answers from text and generate questions about them

## When to choose
- you need to generate questions from text using pre-trained transformer models
- you want simple pipelines for answer-aware or answer-agnostic question generation
- you want to fine-tune seq2seq models like T5 on question generation tasks
- you need to bootstrap QA training data from raw passages

## When to avoid
- you need production-grade, actively maintained NLP pipelines with long-term support
- you want rule-based or template-based question generation without deep learning
- you need question answering rather than question generation
- you cannot run GPU inference or fine-tuning for transformer models

## Facets
- artifact type: library
- maturity: maintenance
- function: nlp, machine-learning, deep-learning, data-generation
- domain: machine-learning, deep-learning
- platform: python
- tags: question-generation, transformers, t5, seq2seq, squad, nlg, natural-language-processing

## Member repositories
- patil-suraj/question_generation (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:44.663076+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:35:24.426184+00:00, confidence not recorded.
  - readme: https://github.com/patil-suraj/question_generation (fetched 2026-08-28T04:03:44.663076+00:00, sha ed4c0e92e280)
- Data as of 2026-08-30T08:39:29.467469+00:00.