pandeykartikey/Hierarchical-Attention-Network
Implementation of Hierarchical Attention Networks in PyTorch
This helps data scientists and machine learning engineers classify documents, like customer reviews or articles, by understanding their natural structure from words to sentences to whole documents. It takes raw text data as input and outputs a classification label for each document. This is ideal for those building document classification systems and looking to leverage advanced neural network architectures.
129 stars. No commits in the last 6 months.
Use this if you need to classify documents and believe that understanding the hierarchy of words and sentences will improve classification accuracy.
Not ideal if you are a business user looking for a ready-to-use document classification application without any programming, or if your documents lack clear sentence and word structures.
Stars
129
Forks
27
Language
Jupyter Notebook
License
—
Category
Last pushed
Oct 22, 2018
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/pandeykartikey/Hierarchical-Attention-Network"
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