Pinned Repositories
bert
TensorFlow code and pre-trained models for BERT
BERT-BiLSTM-CRF
BERT-BiLSTM-CRF的Keras版实现
Bilstm-CRF-Sequence-Labeling
Tensorflow版的BiLSTM-CRF模型
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
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
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
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
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。
Solr-LTR-Training
an exmaple to train LTR model and deploy it on Solr server.
TEDParallelCorpusSpider
ted平行语料爬虫
AidenHuen's Repositories
AidenHuen/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
AidenHuen/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
AidenHuen/BERT-BiLSTM-CRF
BERT-BiLSTM-CRF的Keras版实现
AidenHuen/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。
AidenHuen/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
AidenHuen/Bilstm-CRF-Sequence-Labeling
Tensorflow版的BiLSTM-CRF模型
AidenHuen/Solr-LTR-Training
an exmaple to train LTR model and deploy it on Solr server.
AidenHuen/bert
TensorFlow code and pre-trained models for BERT
AidenHuen/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
AidenHuen/TEDParallelCorpusSpider
ted平行语料爬虫
AidenHuen/toxic-comment-classification
Code and write-up for the Kaggle Toxic Comment Classification Challenge
AidenHuen/attention-networks-for-classification
Hierarchical Attention Networks for Document Classification in PyTorch
AidenHuen/datagrand-text-classification
2018达观杯文本智能处理挑战赛
AidenHuen/EmotionAnalysisForChineseNovels
chinese emotion analysis for Four Great Classical Novels
AidenHuen/homework
AidenHuen/keras
Deep Learning for humans
AidenHuen/Keras-Text-Classifier
AidenHuen/LatticeLSTM
Chinese NER using Lattice LSTM. Code for ACL 2018 paper.
AidenHuen/lucene-solr
Mirror of Apache Lucene + Solr
AidenHuen/Muti-Fea-BLSTM-CRF-FeaProcess
add feature for the BLSTM-CRF
AidenHuen/Recommder
大一下学期，在做新闻推荐系统时的一些代码
AidenHuen/rnn_text_classification
bidirectional rnn for text classification
AidenHuen/smp2018
smp2018 contest ( distinguish human writing or robot writing from news )
AidenHuen/spark
Mirror of Apache Spark
AidenHuen/TensorFlow-Examples
TensorFlow Tutorial and Examples for Beginners (support TF v1 & v2)
AidenHuen/wordSegement
自然语言课堂练习，基于2-gram实现的一个最大概率路径分词