Starred repositories
EasyTransfer is designed to make the development of transfer learning in NLP applications easier.
基于Tensorflow2.3开发的NER模型,都是CRF范式,包含Bilstm(IDCNN)-CRF、Bert-Bilstm(IDCNN)-CRF、Bert-CRF,可微调预训练模型,可对抗学习,用于命名实体识别,配置后可直接运行。
本NER项目包含多个中文数据集,模型采用BiLSTM+CRF、BERT+Softmax、BERT+Cascade、BERT+WOL等,最后用TFServing进行模型部署,线上推理和线下推理。
pytorch实现 Bert 做seq2seq任务,使用unilm方案,现在也可以做自动摘要,文本分类,情感分析,NER,词性标注等任务,支持t5模型,支持GPT2进行文章续写。
EasyRL: An easy-to-use and comprehensive reinforcement learning package.
EasyNLP: A Comprehensive and Easy-to-use NLP Toolkit
TextCNN by TensorFlow 2.0.0 ( tf.keras mainly ).
An Open-Source Package for Neural Relation Extraction (NRE)
Coupled Multi-Layer Attentions for Co-Extraction of Aspect and Opinion Terms
A game theoretic approach to explain the output of any machine learning model.
此项目是机器学习(Machine Learning)、深度学习(Deep Learning)、NLP面试中常考到的知识点和代码实现,也是作为一个算法工程师必会的理论基础知识。
generates music (midi files) using a Tensorflow RNN
Train an LSTM to generate piano or violin/piano music.
General-Purpose Neural Networks for Sentence Boundary Detection
Use BERT to train a classification model and deploy the model by tensorflow serving
brat rapid annotation tool (brat) - for all your textual annotation needs
Super easy library for BERT based NLP models
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
all kinds of text classification models and more with deep learning
Deep neural network framework for multi-label text classification
About Muti-Label Text Classification Based on Neural Network.
A LITE BERT FOR SELF-SUPERVISED LEARNING OF LANGUAGE REPRESENTATIONS, 海量中文预训练ALBERT模型
This repo contains a PyTorch implementation of a pretrained BERT model for multi-label text classification.