textcat
Text classifier
A tool for categorizing text based on its language or content
A Go package for n-gram based text categorization, with support for utf-8 and raw text
72 stars
7 watching
11 forks
Language: Go
last commit: almost 4 years ago
Linked from 3 awesome lists
Related projects:
Repository | Description | Stars |
---|---|---|
goodsign/libtextcat | Provides a Go interface to classify text into languages | 13 |
eaigner/shield | A flexible Bayesian text classifier with backend storage support | 158 |
xiayandi/pytorch_text_classification | An implementation of convolutional neural networks for text classification using PyTorch | 66 |
sergioburdisso/pyss3 | A Python package implementing an interpretable machine learning model for text classification with visualization tools | 336 |
cardmagic/classifier | A module for text classification using Bayesian and Latent Semantic Indexing algorithms | 660 |
2shou/textgrocery | A text classification tool based on LibLinear with support for Chinese tokenize using jieba. | 678 |
ebanalyse/senda | A tool for fine-tuning transformer models for text classification tasks | 19 |
apcode/tensorflow_fasttext | An open-source implementation of a text classification system using word embeddings and TensorFlow. | 302 |
pebbe/go-proj-4 | Provides a limited interface to the Cartographic Projections Library PROJ.4 | 44 |
quarticcat/detypify | An image classification tool designed to recognize typographical symbols | 142 |
mustafaturan/omnicat | A framework providing a generalized strategy holder for text classification | 11 |
mustafaturan/omnicat-bayes | An implementation of the Naive Bayes algorithm as a text classification strategy in Ruby. | 32 |
tpolecat/atto | A compact, incremental text parsing library for Scala that enables efficient and functional processing of structured data | 359 |
tensorflow/text | Preprocessing and processing tools for text data in machine learning models | 1,233 |
djcp/linnaeus | A Redis-backed system for classifying documents into categories based on their content. | 38 |