#97 · Primary category: NLP Tools & Text Processing
Keras-TextClassification
Keras-based toolkit for Chinese text classification, multi-label classification, and sentence similarity with diverse models (FastText, TextCNN, RCNN, BERT, etc.).
Project last updated:06/17/24
GitHub Stars
1.8K
Forks
397
Contributors
2
License
MIT
Why we included this project
Anyone building Chinese text classifiers and wanting to compare architectures side by side will find a handy reference here. The Keras library bundles FastText, TextCNN, TextRNN, RCNN, DPCNN, VDCNN, HAN, capsule networks, and Transformer encoders, plus fine-tuning examples for BERT, XLNet, and ALBERT. Because most models build on shared embedding and network-layer base classes, they run with the same setup, so swapping one for another does not mean restructuring your data pipeline. Working examples for multi-label classification and sentence-pair similarity cover needs beyond plain single-label sorting. Treat it as a study and experimentation toolkit rather than a maintained production framework: some pretrained embeddings and datasets must be downloaded separately, and a few models are still marked as work in progress.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
flair
A very simple framework for state-of-the-art Natural Language Processing (NLP)
compromise
modest natural-language processing
tokenizers
💥 Fast State-of-the-Art Tokenizers optimized for Research and Production
CoreNLP
CoreNLP: A Java suite of core NLP tools for tokenization, sentence segmentation, NER, parsing, coreference, sentiment analysis, etc.
Chinese-Word-Vectors
100+ Chinese Word Vectors 上百种预训练中文词向量