AndyChiangSH/CDGP
Code for Findings of EMNLP 2022 short paper "CDGP: Automatic Cloze Distractor Generation based on Pre-trained Language Model".
This tool helps educators, content creators, and assessment designers efficiently create multiple-choice questions for reading comprehension or vocabulary tests. You provide a sentence or passage (the 'stem') and the correct answer, and it automatically suggests plausible but incorrect options (distractors). This allows you to quickly generate high-quality cloze questions for quizzes, exams, or learning materials.
No commits in the last 6 months.
Use this if you need to rapidly generate effective distractors for cloze-style multiple-choice questions in educational assessments or content.
Not ideal if you require distractor generation for highly specialized, niche domains not covered by general English or scientific texts, or if you need to manually fine-tune every distractor for specific pedagogical reasons.
Stars
14
Forks
4
Language
Jupyter Notebook
License
MIT
Category
Last pushed
May 22, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/AndyChiangSH/CDGP"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
nlpcloud/nlpcloud-python
NLP Cloud serves high performance pre-trained or custom models for NER, sentiment-analysis,...
princeton-nlp/NLProofS
EMNLP 2022: Generating Natural Language Proofs with Verifier-Guided Search...
ysymyth/ec-nl
[ICLR 2022] Linking Emergent and Natural Languages via Corpus Transfer
L-Zhe/CoRPG
Code for paper Document-Level Paraphrase Generation with Sentence Rewriting and Reordering by...
IBM/regen
official code for EMNLP21 paper