cdqa-suite/cdQA
⛔ [NOT MAINTAINED] An End-To-End Closed Domain Question Answering System.
Built on HuggingFace transformers, it combines a dense retriever with a BERT/DistilBERT reader fine-tuned on SQuAD to rank and extract answers from custom document corpora. The system provides data converters (PDF, Markdown) for corpus preparation, supports fine-tuning the reader on custom SQuAD-like datasets, and includes evaluation utilities with weighted retriever-reader score blending for answer ranking.
617 stars. No commits in the last 6 months.
Stars
617
Forks
191
Language
Python
License
Apache-2.0
Category
Last pushed
Apr 30, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/cdqa-suite/cdQA"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related models
AMontgomerie/question_generator
An NLP system for generating reading comprehension questions
KristiyanVachev/Leaf-Question-Generation
Easy to use and understand multiple-choice question generation algorithm using T5 Transformers.
robinniesert/kaggle-google-quest
Google QUEST Q&A Labeling Kaggle Competition 6th Place Solution
cooelf/AwesomeMRC
IJCAI 2021 Tutorial & code for Retrospective Reader for Machine Reading Comprehension (AAAI 2021)
pranavkumaarofficial/nlcli-wizard
Natural language control for Python CLI tools using locally-trained SLMs (CPU inference)