hdltex:文本分类的分层深度学习
HDLTex的Python项目详细描述
hdltex:文本分类的分层深度学习
参考文件:HDLTex: Hierarchical Deep Learning for Text Classification
安装
使用pip
pip install HDLTex
使用git
git clone --recursive https://github.com/kk7nc/HDLTex.git
这个包的主要需求是带有tensorflow的python 3。 requirements.txt文件包含所需python的列表 软件包;要安装所有要求,请运行以下命令:
pip -r install requirements.txt
或
pip3 install -r requirements.txt
或:
conda install --file requirements.txt
如果上述命令不起作用,请使用以下命令:
sudo -H pip install -r requirements.txt
文档:
hdltex的数据集:
科学网络数据集 WOS-11967
This dataset contains 11,967 documents with 35 categories which include 7 parents categories.
科学网络数据集 WOS-46985
This dataset contains 46,985 documents with 134 categories which include 7 parents categories.
科学网络数据集 WOS-5736
This dataset contains 5,736 documents with 11 categories which include 3 parents categories.
要求:
概述:
python 3.5或更高版本请参见Instruction Documents
scikit学习参见Instruction Documents
GPU:
CUDA工具包8.0。有关详细信息,请参见NVIDIA’s documentation。
那是NVIDIA drivers associated with CUDA Toolkit 8.0。
Cudnn V6。有关详细信息,请参见NVIDIA’s documentation。
具有CUDA计算能力3.0或更高版本的GPU卡。
libcupti开发库,
要安装此库,请发出以下命令:
$ sudo apt-get install libcupti-dev
特征提取:
单词表示的全局向量 (GLOVE)
For CNN and RNN you need to download and linked the folder location to GLOVE
错误和注释:
向kk7nc@virginia.edu发送电子邮件
引文:
@inproceedings{Kowsari2018HDLTex, author={Kowsari, Kamran and Brown, Donald E and Heidarysafa, Mojtaba and Meimandi, Kiana Jafari and Gerber, Matthew S and Barnes, Laura E}, booktitle={2017 16th IEEE International Conference on Machine Learning and Applications (ICMLA)}, title={HDLTex: Hierarchical Deep Learning for Text Classification}, year={2017}, pages={364-371}, doi={10.1109/ICMLA.2017.0-134}, month={Dec}}