Discover @AidenHuen Open Source projects

Aiden Huen (@AidenHuen)

AidenHuen

Stars
215
Global Rank 115,802 (Top 5 %)
Followers 36
Following 17
Registered over 9 years ago
Most used languages

Python
75.0 %

Java
25.0 %
Location 🇨🇳 China
Country Total Rank 14,590
Country Ranking

Python
2,862

Capsule-Text-Classification

利用keras搭建的胶囊网络（capsule network文本分类模型，包含RNN、CNN、HAN等，其中keras_utils包含了capsule层和attention层的keras实现

FGN-NER

The source code of 《 FGN：Fusion Glyph Network for Chinese Named Entity Recognition 》. SOTA Chinese NER method fusing both glyph represnetation and BERT representation

BERT-BiLSTM-CRF

BERT-BiLSTM-CRF的Keras版实现

SMP-Keyword-Extraction

CSDN博客的关键词提取算法，融合TF，IDF，词性，位置等多特征。该项目用于参加2017 SMP用户画像测评，排名第四,在验证集中精度为59.9%，在最终集中精度为58.7%。启发式的方法，通用性强。

Chinese-Character-Feature-Resource

This repo contain images,radicals,meaning radical and Pinyin for more than 6000 Chinese character. The image set inculde both traditional Chinese and simple Chinese

Solr-LTR-Training

an exmaple to train LTR model and deploy it on Solr server.

Bilstm-CRF-Sequence-Labeling

Tensorflow版的BiLSTM-CRF模型

TEDParallelCorpusSpider

ted平行语料爬虫

HMM-NER

基于隐马尔科夫模型的中文命名实体识别模型源码，语料源于2014年人民日报标注集