KristiyanVachev/Question-Generation
A question generation system that uses machine learning to extract keywords from text and generate multiple choice quiz questions.
Not currently ranked — collecting fresh signals.
star history
This project generates multiple choice questions from text by identifying keywords as potential answers, replacing them with blanks to form question bases, transforming sentences into question format, and generating similar-word distractors as incorrect options. It employs spacy for NLP processing, naive bayes for classification, word embeddings and cosine similarity for keyword and distractor identification. The approach has been published at RANLP2021 conference and evolved to use T5 transformers in a related repository.
Frequently asked
- What is KristiyanVachev/Question-Generation?
- A question generation system that uses machine learning to extract keywords from text and generate multiple choice quiz questions.
- Is Question-Generation open source?
- Yes — KristiyanVachev/Question-Generation is open source, released under the GPL-3.0 license.
- What language is Question-Generation written in?
- KristiyanVachev/Question-Generation is primarily written in Jupyter Notebook.
- How popular is Question-Generation?
- KristiyanVachev/Question-Generation has 494 stars on GitHub.
- Where can I find Question-Generation?
- KristiyanVachev/Question-Generation is on GitHub at https://github.com/KristiyanVachev/Question-Generation.