MurtyShikhar/Question-Answering

TensorFlow implementation of Match-LSTM and Answer pointer for the popular SQuAD dataset.

41
/ 100
Emerging

This project helps researchers and students studying natural language processing to train a question-answering model. You feed it a collection of text documents (like articles or passages) and corresponding questions, and it produces a model capable of finding answers within new text. This is designed for those exploring deep learning architectures for text comprehension.

135 stars. No commits in the last 6 months.

Use this if you are a machine learning researcher or student who wants to experiment with or understand the Match-LSTM and Answer Pointer neural network architecture for question answering.

Not ideal if you need a ready-to-use, high-performance question-answering system for practical application, as this is a research implementation focused on reproducing an academic paper.

natural-language-processing machine-learning-research question-answering deep-learning text-comprehension
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 23 / 25

How are scores calculated?

Stars

135

Forks

67

Language

Python

License

Last pushed

Feb 15, 2018

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/MurtyShikhar/Question-Answering"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.