Rooooyy/HiTIN
Code for ACL 2023 paper "HiTIN: Hierarchy-aware Tree Isomorphism Network for Hierarchical Text Classification"
This project helps researchers and data scientists categorize text documents into pre-defined, multi-level hierarchies, like assigning a news article to 'World' then 'Politics' then 'International Relations'. You provide raw text documents and their associated hierarchical categories, and it outputs a trained model that can automatically classify new documents with high accuracy, respecting the relationships between categories. It is designed for those working with large volumes of text that need organized, nested classification.
No commits in the last 6 months.
Use this if you need to classify documents into a hierarchy of categories and want to leverage the relationships between those categories for more accurate results.
Not ideal if you only need flat (non-hierarchical) text classification or if you do not have pre-existing hierarchical labels for your data.
Stars
38
Forks
5
Language
Python
License
—
Category
Last pushed
Mar 27, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Rooooyy/HiTIN"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
philipperemy/keras-attention
Keras Attention Layer (Luong and Bahdanau scores).
tatp22/linformer-pytorch
My take on a practical implementation of Linformer for Pytorch.
datalogue/keras-attention
Visualizing RNNs using the attention mechanism
ematvey/hierarchical-attention-networks
Document classification with Hierarchical Attention Networks in TensorFlow. WARNING: project is...
thushv89/attention_keras
Keras Layer implementation of Attention for Sequential models