NLP/Keras-TextClassification

Fork 0

中文长文本分类、短句子分类、多标签分类、两句子相似度（Chinese Text Classification of Keras NLP, multi-label classify, or sentence classify, long or short），字词句向量嵌入层（embeddings）和网络层（graph）构建基类，FastText，TextCNN，CharCNN，TextRNN, RCNN, DCNN, DPCNN, VDCNN, CRNN, Bert, Xlnet, Albert, Attention, DeepMoji, HAN, 胶囊网络-CapsuleNet, Transformer-encode, Seq2seq, SWEM, LEAM, TextGCN

albert bert capsule charcnn crnn dcnn dpcnn embeddings fasttext han keras keras-textclassification leam nlp rcnn text-classification textcnn transformer vdcnn xlnet

Go to file

yongzhuo 164be1eb0a add CapsuleNet-bojone of NLP		2019-07-19 19:00:03 +08:00
keras_textclassification	add CapsuleNet-bojone of NLP	2019-07-19 19:00:03 +08:00
test	重构代码,新增CapsuleNet	2019-07-12 02:37:48 +08:00
__init__.py	Add files via upload	2019-06-13 23:34:38 +08:00
.gitignore	Initial commit	2019-06-13 23:02:32 +08:00
LICENSE	Initial commit	2019-06-13 23:02:32 +08:00
README.md	HAN debug	2019-07-15 10:34:33 +08:00
requirements.txt	Add files via upload	2019-06-13 23:34:38 +08:00
setup.py	Add files via upload	2019-07-05 02:06:50 +08:00

README.md

Keras-TextClassification

keras_textclassification（代码主体,未完待续...）

- Bert-fineture
- FastText
- TextCNN
- charCNN
- TextRNN
- TextRCNN
- TextDCNN
- TextDPCNN
- TextVDCNN
- TextCRNN
- DeepMoji
- SelfAttention
- HAN
- CapsuleNet

run(运行, 以FastText为例)

- 1. 进入keras_textclassification/m01_FastText目录，
- 2. 训练: 运行 train.py,   例如: python train.py
- 3. 预测: 运行 predict.py, 例如: python predict.py
- 说明: 默认不带pre train的random embedding，训练和验证语料只有100条，完整语料移步下面data查看下载

run(test/sample实例)

- bert,word2vec,random样例在test/目录下, 注意word2vec(char or word), random-word,  bert(chinese_L-12_H-768_A-12)未全部加载,需要下载
- predict_bert_text_cnn.py
- tet_char_bert_embedding.py
- tet_char_random_embedding.py
- tet_char_word2vec_embedding.py
- tet_word_random_embedding.py
- tet_word_word2vec_embedding.py

keras_textclassification/data

- 数据下载
  ** github项目中只是上传部分数据，需要的前往链接: https://pan.baidu.com/s/1I3vydhmFEQ9nuPG2fDou8Q 提取码: rket
- baidu_qa_2019（百度qa问答语料，只取title作为分类样本，17个类，有一个是空''，已经压缩上传）
   - baike_qa_train.csv
   - baike_qa_valid.csv
- embeddings
   - chinese_L-12_H-768_A-12/(取谷歌预训练好点的模型，已经压缩上传)
   - term_char.txt(已经上传, 项目中已全, wiki字典, 还可以用新华字典什么的)
   - term_word.txt(未上传, 项目中只有部分, 可参考词向量的)
   - w2v_model_merge_short.vec(未上传, 项目中只有部分, 词向量, 可以用自己的)
   - w2v_model_wiki_char.vec(已上传百度网盘, 项目中只有部分, 自己训练的维基百科字向量, 可以用自己的)
- model
   - 预训练模型存放地址

项目说明

1. 构建了base基类(网络(graph)、向量嵌入(词、字、句子embedding)),后边的具体模型继承它们，代码简单
1. conf存放项目数据、模型的地址, data存放数据和语料, etl为数据预处理模块,

模型与论文paper题与地址

FastText: Bag of Tricks for Efﬁcient Text Classiﬁcation
TextCNN： Convolutional Neural Networks for Sentence Classiﬁcation
charCNN： Character-Aware Neural Language Models
TextRNN： Recurrent Neural Network for Text Classification with Multi-Task Learning
RCNN： Recurrent Convolutional Neural Networks for Text Classification
DCNN: A Convolutional Neural Network for Modelling Sentences
DPCNN: Deep Pyramid Convolutional Neural Networks for Text Categorization
VDCNN: Very Deep Convolutional Networks
CRNN: A C-LSTM Neural Network for Text Classification
DeepMoji: Using millions of emojio ccurrences to learn any-domain represent ations for detecting sentiment, emotion and sarcasm
SelfAttention: Attention Is All You Need
HAN: Hierarchical Attention Networks for Document Classification
CapsuleNet: Dynamic Routing Between Capsules

参考/感谢

文本分类项目: https://github.com/mosu027/TextClassification
文本分类看山杯: https://github.com/brightmart/text_classification
Kashgari项目: https://github.com/BrikerMan/Kashgari
文本分类Ipty : https://github.com/lpty/classifier
keras文本分类: https://github.com/ShawnyXiao/TextClassification-Keras
keras文本分类: https://github.com/AlexYangLi/TextClassification

README.md Unescape Escape