bcol23/HyperIM
PyTorch implementation of the paper "Hyperbolic Interaction Model For Hierarchical Multi-Label Classification"
This project helps machine learning researchers and data scientists classify documents into multiple categories, especially when those categories have a hierarchical relationship. It takes text data and a hierarchy of labels as input, then outputs predictions for which labels apply to each document. This is ideal for those working on complex text classification problems where labels are structured.
No commits in the last 6 months.
Use this if you need to classify text documents into several categories at once, and these categories are organized in a parent-child hierarchy (e.g., 'Science' -> 'Biology' -> 'Botany').
Not ideal if your classification labels are flat and have no hierarchical relationships, or if you are not comfortable working with Python code and data formats like NumPy arrays.
Stars
49
Forks
11
Language
Python
License
MIT
Category
Last pushed
Sep 04, 2019
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/bcol23/HyperIM"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
carpedm20/lstm-char-cnn-tensorflow
in progress
ilivans/tf-rnn-attention
Tensorflow implementation of attention mechanism for text classification tasks.
ahmedbesbes/character-based-cnn
Implementation of character based convolutional neural network
AlexGidiotis/Document-Classifier-LSTM
A bidirectional LSTM with attention for multiclass/multilabel text classification.
NonvolatileMemory/AAAI_2019_EXAM
Official implementation of "Explicit Interaction Model towards Text Classification"