Natural Language Understanding Python Packages

tokenizers

💥 Fast State-of-the-Art Tokenizers optimized for Research and Production

214.2M 11K 1K

drug-named-entity-recognition

Drug Named Entity Recognition library to find and resolve drug names in a string (drug named entity linking)

88K 33 14

autotrain-advanced

🤗 AutoTrain Advanced

37K 5K 626

adaseq

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

37K 454 44

gluonnlp

NLP made easy

24K 3K 520

tokenizers-gt

💥 Fast State-of-the-Art Tokenizers optimized for Research and Production

6K 11K 1K

bert-tensorflow

TensorFlow code and pre-trained models for BERT

6K 40K 10K

autonlp

🤗 AutoTrain Advanced

4K 5K 626

imodelsx

Interpret text data with LLMs (sklearn compatible).

3K 176 27

stark-engine

S.T.A.R.K. - Speech And Text Algorithmic Recognition Kit

3K 62 4

bert-qa

Accelerating the development of question-answering systems based on BERT and TF 2.0

3K 20 4

pvrhino

On-device Speech-to-Intent engine powered by deep learning

3K 703 95

articutapi

API of Articut 中文斷詞 (兼具語意詞性標記)：「斷詞」又稱「分詞」，是中文資訊處理的基礎。Articut 不用機器學習，不需資料模型，只用現代白話中文語法規則，即能達到 SIGHAN 2005 F1-measure 94% 以上，Recall 96% 以上的成績。

3K 415 37

oneai

Python SDK for One AI APIs. One AI is an NLP-as-a-service platform. Our APIs enables language comprehension in context, transforming texts from any source into structured data to use in code.

2K 38 7

deberta

The implementation of DeBERTa

2K 2K 237

textfeatureselection

Python library for feature selection for text features. It has filter method, genetic algorithm and TextFeatureSelectionEnsemble for improving text classification models. Helps improve your machine learning models

2K 53 5