littlepai

Unofficial-Zhihu-API

深度学习模型自动识别验证码，python爬虫库自动管理会话，通过简单易用的API，实现知乎数据的爬取

allennlp-models

Officially supported AllenNLP models

Articles

:notebook_with_decorative_cover: 简书文章中的材料

BEFAQ

FAQ-based Question Answering System using BERT

bert

TensorFlow code and pre-trained models for BERT

Chinese-Text-Classification-Pytorch

中文文本分类，TextCNN，TextRNN，FastText，TextRCNN，BiLSTM_Attention，DPCNN，Transformer，基于pytorch，开箱即用。

chinese_chatbot_corpus

中文公开聊天语料库

ChineseNLPCorpus-1

中文自然语言处理数据集，平时做做实验的材料。欢迎补充提交合并。

CLUEPretrainedModels

高质量中文预训练模型集合：最先进大模型、最快小模型、相似度专门模型

corpus

自然语言处理，知识图谱相关语料。按照Task细分，欢迎PR。

CrossWOZ

A Large-Scale Chinese Cross-Domain Task-Oriented Dialogue Dataset

DeepNER

天池中药说明书实体识别挑战冠军方案；中文命名实体识别；NER; BERT-CRF & BERT-SPAN & BERT-MRC；Pytorch

EffectiveModernCppChinese

《Effective Modern C++》翻译 - 2019.6更新中

EVA

hugegraph

HugeGraph Database core component, including graph engine, API, and built-in backends

lasertagger

mt-dnn

Multi-Task Deep Neural Networks for Natural Language Understanding

open_model_zoo

Pre-trained Deep Learning models and demos (high quality and extremely fast)

pretrained-models

Open Language Pre-trained Model Zoo

pytorch-crf

(Linear-chain) Conditional random field in PyTorch.

QueryGeneration

sentence-transformers

Sentence Embeddings with BERT & XLNet

service-streamer

Boosting your Web Services of Deep Learning Applications.

simbert

a bert for retrieval and generation

Text-Recognition-Material

Papers, Datasets, Algorithms, SOTA for STR. Long-time Maintaining

text_data_enhancement_with_LaserTagger

Modify Chinese text, modified on LaserTagger Model. 文本复述，基于lasertagger做中文文本数据增强。

TreebankPreprocessing

Python scripts preprocessing Penn Treebank and Chinese Treebank

unstructured

OCR似乎比百度的paddle ocr好用

WeChatExtension-ForMac

Mac微信功能拓展/微信插件/微信小助手(A plugin for Mac WeChat)

xf_event_extraction2020Top1

科大讯飞2020事件抽取挑战赛第一名解决方案&完整事件抽取系统