xmnlp

Why we included this project

xmnlp is one pip install that covers the routine Chinese text-processing jobs most projects end up needing: tokenization, part-of-speech tagging, and named entity recognition on a RoBERTa + CRF backbone, plus sentiment analysis, spell checking, pinyin conversion, radical lookup, and TextRank-based keyword and summary extraction. That breadth saves teams building search backends, content pipelines, or QA tooling for Chinese-language products from wiring together several libraries. Segmentation and tagging each come in fast and deep variants, so you have a speed lever when working through long documents. Models download separately and the project has been quiet since 2022, so treat it as a pragmatic, low-maintenance choice rather than something you'd build ongoing production work on.