DevSinghSachan/emdr2
Code and Models for the paper "End-to-End Training of Multi-Document Reader and Retriever for Open-Domain Question Answering" (NeurIPS 2021)
This is a framework for researchers and developers working on open-domain question answering systems. It provides a method to train models that can efficiently search through a large collection of documents (like Wikipedia) to find the most relevant information and then extract a precise answer to a user's question. The input is a question and a body of text, and the output is a direct answer.
110 stars. No commits in the last 6 months.
Use this if you are developing or experimenting with advanced question-answering systems that need to find answers within vast document corpuses.
Not ideal if you are looking for a ready-to-use, off-the-shelf question-answering application or do not have experience with machine learning model training and infrastructure.
Stars
110
Forks
11
Language
Python
License
—
Category
Last pushed
Apr 18, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/DevSinghSachan/emdr2"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
asahi417/lm-question-generation
Multilingual/multidomain question generation datasets, models, and python library for question...
SparkJiao/SLQA
An Unofficial Pytorch Implementation of Multi-Granularity Hierarchical Attention Fusion Networks...
MurtyShikhar/Question-Answering
TensorFlow implementation of Match-LSTM and Answer pointer for the popular SQuAD dataset.
hsinyuan-huang/FlowQA
Implementation of conversational QA model: FlowQA (with slight improvement)
allenai/aokvqa
Official repository for the A-OKVQA dataset