Text-GCN and Bible_Text_GCN
These are independently reimplemented versions of the same seminal GCN paper for text classification with nearly identical functionality, making them competitors rather than complementary tools.
About Text-GCN
kenqgu/Text-GCN
A PyTorch implementation of "Graph Convolutional Networks for Text Classification." (AAAI 2019)
This project helps you categorize text documents quickly and accurately, even with limited training data. You provide a collection of documents and their assigned categories (or some of them), and it outputs a model that can predict categories for new documents. It also generates meaningful representations for your words and documents. This is ideal for data scientists, NLP practitioners, or researchers needing robust text classification.
About Bible_Text_GCN
plkmo/Bible_Text_GCN
Pytorch implementation of "Graph Convolutional Networks for Text Classification"
This project helps religious scholars, theologians, or Bible study enthusiasts automatically categorize segments of biblical text. It takes unlabelled chapters or passages and classifies them into their correct books (e.g., Genesis, Exodus) based on patterns learned from other labelled chapters. This is particularly useful for analyzing large volumes of text where manual classification would be time-consuming.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work