Guan Wang

Awesome-Chinese-NLP. A curated list of resources for Chinese NLP 中文自然语言处理相关资料

Information-Extraction-Chinese. Chinese Named Entity Recognition with IDCNN/biLSTM+CRF, and Relation Extraction with biGRU+2ATT 中文实体识别与关系提取

Rasa_NLU_Chi. Turn Chinese natural language into structured data 中文自然语言理解

Small-Chinese-Corpus. Some useful Chinese corpus datasets 中文语料小数据

Somiao-Pinyin. Somiao Pinyin: Train your own Chinese Input Method with Seq2seq Model 搜喵拼音输入法

text2vec. Easily generate document/paragraph/sentence vectors and calculate similarity.

Chinese-VQA. Chinese Visual Question Answering 中文看图问答

federated_shap. Code for paper "Interpret Federated Learning with Shapley Values"

hk_ipo_prediction. Predict first day performance of Hong Kong IPO stocks: A pipeline example of machine learning projects

Geetest-Captcha-Crack. Geetest Captcha Crack 为了不被怪兽吃掉而奋斗！

aiml_chatbot. AIML based chatbot

lstm_text_generation_chinese. Chinese Text Generation using LSTM

crownpku.github.io. personal blog

Responsible-AI. This is a demo project of using Responsible AI technology provided by Google to build responsible machine learning applications.

learning_materials. A collection of personal learning materials.

Question_Answering_UI. A Simple UI based on Dash for Question Answering

CDial-GPT. A Large-scale Chinese Short-Text Conversation Dataset and Chinese pre-training dialog models

share_everything. wechat public account share_everything code

Awesome-Insurance. A curated list of insurance related technology across the business line

end_to_end_cnn_captcha. End to end Captcha Crack with CNN

sen_simi_cal. Calculate sentence similarity by word vector

spaCy. 💫 Industrial-strength Natural Language Processing (NLP) with Python and Cython

spacy-course. 👩‍🏫 Advanced NLP with spaCy: A free online course

stanford-corenlp-python. Python wrapper for Stanford CoreNLP tools v3.7.0, modified for Chinese

live_traffic_crawler. 实时交通热力图数据获取

rasa_core. machine learning based dialogue engine for AI assistants

rasa_nlu. turn natural language into structured data

tunix-gemma4-tpu. This repository contains the complete workflow for fine-tuning the Gemma 4 E2B-IT (5.1B) model on the insuranceQA-v2 dataset using Tunix (JAX) on Google Cloud TPUs.

CommunityDetection. CommunityDetection

wikiextractor. A tool for extracting plain text from Wikipedia dumps

of. on Opinion Formation

bot5.club. Bot Friday Club - BOT5

ydata-synthetic. Open repository with GAN architectures for tabular data implemented using Tensorflow 2.0.

ParallelGA. Objective-C

FATE. An Industrial Level Federated Learning Framework for the Federated AI ecosystem

DamageSpreading. C++