ExtractThinker is a Document Intelligence library for LLMs
The Classical Language Toolkit
Stanford NLP Python library for many human languages
Public opinion analysis system
A Repo For Document AI
Persian NLP Toolkit
DataDreamer: Prompt. Generate Synthetic Data. Train & Align Models
Obsei is a low code AI powered automation tool
Resources, corpora, and tools for Chinese natural language processing
fastNLP: A Modularized and Extensible NLP Framework
We describe a simple XML format to share text documents and annotation