Search Packages

seqeval

A Python framework for sequence labeling evaluation(named-entity recognition, pos tagging, etc...)

nagisa

A Japanese tokenizer based on recurrent neural networks

flair

A very simple framework for state-of-the-art Natural Language Processing (NLP)

adaseq

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

bi-lstm-crf

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

group-appeal-detector

Automated detection of social group appeals in text

delft

a Deep Learning Framework for Text https://delft.readthedocs.io/

morphseg

An efficient and easy-to-use morpheme segmentation library

transformers-keras

Transformer-based models implemented in tensorflow 2.x(Keras)

kashgari

Simple, Keras-powered multilingual NLP framework, allows you to build your models in 5 minutes for named entity recognition (NER), part-of-speech tagging (PoS) and text classification tasks. Includes BERT, GPT-2 and word2vec embedding.

band

BAND：BERT Application aNd Deployment, A simple and efficient BERT model training and deployment framework.

qiznlp

Quick run NLP in many task 快速运行分类、序列标注、匹配、生成等NLP任务的Tensorflow框架 (中文 NLP 支持分布式）

nlp-toolkit

Basic NLP Toolkits include text classification, sequence labeling etc.

anago

Bidirectional LSTM-CRF and ELMo for Named-Entity Recognition, Part-of-Speech Tagging and so on.

kashgari-tf

Kashgari is a production-level NLP Transfer learning framework built on top of tf.keras for text-labeling and text-classification, includes Word2Vec, BERT, and GPT2 Language Embedding.

nerval

Entity-level confusion matrix and classification report to evaluate Named Entity Recognition (NER) models.

lightner

Inference with state-of-the-art models (pre-trained by LD-Net / AutoNER / VanillaNER / ...)

iohmm

A python library for Input Output Hidden Markov Models

econll

Extended CoNLL Utilities for Shallow Parsing

fasthmm

A python package for HMM model with fast train and decoding implementation

musket-text

Text support for Musket ML

pytorch-nlu

中文文本分类、序列标注工具包（pytorch），支持中文长文本、短文本的多类、多标签分类任务，支持中文命名实体识别、词性标注、分词、抽取式文本摘要等序列标注任务。 Chinese text classification and sequence labeling toolkit, supports multi class and multi label classification, text similsrity, text summary and NER.

ws-benchmark

[NeurIPS 2021] WRENCH: Weak supeRvision bENCHmark

macadam

Joint-NER-and-RE