🦜🔗 Build context-aware reasoning applications

Tensor library for machine learning

EMNLP'2021: SimCSE: Simple Contrastive Learning of Sentence Embeddings

NLP Core Library and Model Zoo based on PaddlePaddle 2.0

PArallel Distributed Deep LEarning （PaddlePaddle核心框架，高性能单机、分布式训练和跨平台部署）

课程视频、PPT和源代码：侯捷C++系列；台大郭彦甫MATLAB

A toolkit to manage pretrained models of PaddlePaddle and start transfer learning more efficiently.

Pre-trained and Reproduced Deep Learning Models （经典复现模型）

Data loaders and abstractions for text and NLP

Sentence Embeddings with BERT & XLNet

Documentations for PaddlePaddle

Baidu's open-source Sentiment Analysis System.

🤗 Transformers: State-of-the-art Natural Language Processing for Pytorch and TensorFlow 2.0.

基于飞桨的OCR工具库，包含总模型仅8.6M的超轻量级中文OCR，单模型支持中英文数字组合识别、竖排文本识别、长文本识别。同时支持多种文本检测、文本识别的训练算法。

hapi is a High-level API that supports both static and dynamic execution modes (still under development)

novel deep learning research works with PaddlePaddle

Module repo of PaddleHub

结巴中文分词

Reference models and tools for Cloud TPUs.

An open source AutoML toolkit for neural architecture search and hyper-parameter tuning.

An unofficial Gluon FR Toolkit for face recognition. https://gluon-face.readthedocs.io

大规模中文自然语言处理语料 Large Scale Chinese Corpus for NLP

Natural Language Processing Best Practices & Examples

An Open-source Neural Hierarchical Multi-label Text Classification Toolkit

XLNet: Generalized Autoregressive Pretraining for Language Understanding

Open Chinese Language Pre-trained Model Zoo

2019年最新总结，阿里，腾讯，百度，美团，头条等技术面试题目，以及答案，专家出题人分析汇总。