inspirehep/magpie
Deep neural network framework for multi-label text classification
Builds word2vec embeddings and trains Keras neural networks on paired text/label files, with configurable train-test splitting and memory-efficient batch processing for large datasets. Returns confidence-scored predictions across all labels rather than single classifications. Originally developed at CERN for Physics abstract categorization, supporting custom label sets and model persistence across word vectors, scalers, and trained weights.
688 stars. No commits in the last 6 months.
Stars
688
Forks
190
Language
Python
License
MIT
Category
Last pushed
Jan 31, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/inspirehep/magpie"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
davidberenstein1957/classy-classification
This repository contains an easy and intuitive approach to few-shot classification using...
kk7nc/Text_Classification
Text Classification Algorithms: A Survey
AnubhavGupta3377/Text-Classification-Models-Pytorch
Implementation of State-of-the-art Text Classification Models in Pytorch
castorini/hedwig
PyTorch deep learning models for document classification
dayyass/text-classification-baseline
Pipeline for fast building text classification TF-IDF + LogReg baselines.