Word Segmentation Python Packages

sentencepiece

Unsupervised text tokenizer for Neural Network-based text generation.

pythainlp

Thai natural language processing in Python

symspellpy

Python port of SymSpell: 1 million times faster spelling correction & fuzzy search through Symmetric Delete spelling correction algorithm

kiwipiepy

Python API for Kiwi

nagisa

A Japanese tokenizer based on recurrent neural networks

kiwipiepy-model

Python API for Kiwi

bi-lstm-crf

A PyTorch implementation of the BI-LSTM-CRF model.

adaseq

AdaSeq: An All-in-One Library for Developing State-of-the-Art Sequence Understanding Models

pycantonese

Cantonese Linguistics and NLP

rustling

A high-performance library for computational linguistics

youtokentome

Unsupervised text tokenizer focused on computational efficiency

bert-multitask-learning

BERT for Multitask Learning

wordseg

Word segmentation models

tf-sentencepiece

Unsupervised text tokenizer for Neural Network-based text generation.

kitoken

Fast tokenizer for language models, compatible with SentencePiece, Tokenizers, Tiktoken and more. Supports BPE, Unigram and WordPiece tokenization in JavaScript, Python and Rust.

ekphrasis

Ekphrasis is a text processing tool, geared towards text from social networks, such as Twitter or Facebook. Ekphrasis performs tokenization, word normalization, word segmentation (for splitting hashtags) and spell correction, using word statistics from 2 big corpora (english Wikipedia, twitter - 330mil english tweets).

lac

百度NLP：分词，词性标注，命名实体识别，词重要性

vncorenlp

A Python wrapper for VnCoreNLP using a bidirectional communication channel.

hellonlp

NLP tools, word segmentation, sentence segmentation， New-Word-Discovery，新词发现

cjieba

Python cffi binding for cjieba

symspellcpppy

Fast SymSpell written in c++ and exposes to python via pybind11

hanlperceptron

Native Python HanLP Perceptron Model: HanLPerceptron 中文斷詞 詞性標註 命名實體識別

hashformers

Accurate word segmentation for hashtags and text, powered by Transformers and Beam Search. A scalable alternative to heuristic splitters and massive LLMs.

toiro

A tool for comparing tokenizers