Skip to content

Commit e2197a0

Browse files
kk7nckk7nc
authored
Create README.rst
1 parent 54f4dbb commit e2197a0

1 file changed

Lines changed: 172 additions & 0 deletions

File tree

‎code/HDLTex/README.rst‎

Lines changed: 172 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,172 @@
1+
|DOI| |travis| |appveyor| |wercker status| |Join the chat at
2+
https://gitter.im/HDLTex| |arXiv| |RG| |Binder| |license| |twitter|
3+
4+
HDLTex: Hierarchical Deep Learning for Text Classification
5+
==========================================================
6+
7+
Refrenced paper : `HDLTex: Hierarchical Deep Learning for Text
8+
Classification <https://arxiv.org/abs/1709.08267>`__
9+
10+
.. image:: /docs/pic/github-logo.png
11+
:target: https://github.com/kk7nc/HDLTex
12+
13+
14+
|Pic|
15+
16+
Documentation:
17+
===============
18+
19+
Increasingly large document collections require improved information processing methods for searching, retrieving, and organizing text. Central to these information processing methods is document classification, which has become an important application for supervised learning. Recently the performance of traditional supervised classifiers has degraded as the number of documents has increased. This is because along with growth in the number of documents has come an increase in the number of categories. This paper approaches this problem differently from current document classification methods that view the problem as multi-class classification. Instead we perform hierarchical classification using an approach we call Hierarchical Deep Learning for Text classification (HDLTex). HDLTex employs stacks of deep learning architectures to provide specialized understanding at each level of the document hierarchy.
20+
21+
Installation
22+
=============
23+
24+
Using pip
25+
----------
26+
.. code:: bash
27+
28+
pip install HDLTex
29+
30+
Using git
31+
----------
32+
.. code:: bash
33+
34+
git clone --recursive https://github.com/kk7nc/HDLTex.git
35+
36+
37+
The primary requirements for this package are Python 3 with Tensorflow.
38+
The requirements.txt file contains a listing of the required Python
39+
packages; to install all requirements, run the following:
40+
41+
.. code:: bash
42+
43+
pip -r install requirements.txt
44+
45+
Or
46+
47+
.. code:: bash
48+
49+
pip3 install -r requirements.txt
50+
51+
Or:
52+
53+
.. code:: bash
54+
55+
conda install --file requirements.txt
56+
57+
58+
If the above command does not work, use the following:
59+
60+
.. code:: bash
61+
62+
sudo -H pip install -r requirements.txt
63+
64+
65+
Datasets for HDLTex:
66+
=====================
67+
68+
Linke of dataset: |Data|
69+
70+
Web of Science Dataset
71+
`WOS-11967 <http://dx.doi.org/10.17632/9rw3vkcfy4.2>`__
72+
73+
::
74+
75+
This dataset contains 11,967 documents with 35 categories which include 7 parents categories.
76+
77+
78+
Web of Science Dataset
79+
`WOS-46985 <http://dx.doi.org/10.17632/9rw3vkcfy4.2>`__
80+
81+
::
82+
83+
This dataset contains 46,985 documents with 134 categories which include 7 parents categories.
84+
85+
86+
Web of Science Dataset
87+
`WOS-5736 <http://dx.doi.org/10.17632/9rw3vkcfy4.2>`__
88+
89+
::
90+
91+
This dataset contains 5,736 documents with 11 categories which include 3 parents categories.
92+
93+
Requirements :
94+
----------------
95+
General:
96+
97+
- Python 3.5 or later see `Instruction Documents <https://www.python.org/>`__
98+
- TensorFlow see `Instruction Documents <https://www.tensorflow.org/install/install_linux>`__.
99+
- scikit-learn see `Instruction Documents <http://scikit-learn.org/stable/install.html>`__
100+
- Keras see `Instruction Documents <https://keras.io/>`__
101+
- scipy see `Instruction Documents <https://www.scipy.org/install.html>`__
102+
- GPU
103+
104+
- CUDA® Toolkit 8.0. For details, see `NVIDIA’s documentation <https://developer.nvidia.com/cuda-toolkit>`__.
105+
- The `NVIDIA drivers associated with CUDA Toolkit 8.0 <http://www.nvidia.com/Download/index.aspx>`__.
106+
- cuDNN v6. For details, see `NVIDIA’s documentation <https://developer.nvidia.com/cudnn>`__.
107+
- GPU card with CUDA Compute Capability 3.0 or higher.
108+
- The libcupti-dev library,
109+
- To install this library, issue the following command:
110+
111+
::
112+
113+
$ sudo apt-get install libcupti-dev
114+
115+
116+
Feature Extraction:
117+
===================
118+
119+
Global Vectors for Word Representation
120+
(`GLOVE <https://nlp.stanford.edu/projects/glove/>`__)
121+
122+
::
123+
124+
For CNN and RNN you need to download and linked the folder location to GLOVE
125+
126+
127+
128+
Error and Comments:
129+
===================
130+
131+
Send an email to kk7nc@virginia.edu
132+
133+
Citation:
134+
=========
135+
136+
.. code:: bash
137+
138+
@inproceedings{Kowsari2018HDLTex,
139+
author={Kowsari, Kamran and Brown, Donald E and Heidarysafa, Mojtaba and Meimandi, Kiana Jafari and Gerber, Matthew S and Barnes, Laura E},
140+
booktitle={2017 16th IEEE International Conference on Machine Learning and Applications (ICMLA)},
141+
title={HDLTex: Hierarchical Deep Learning for Text Classification},
142+
year={2017},
143+
pages={364-371},
144+
doi={10.1109/ICMLA.2017.0-134},
145+
month={Dec}
146+
}
147+
148+
.. |DOI| image:: http://kowsari.net/HDLTex_DOI.svg?maxAge=2592000
149+
:target: https://doi.org/10.1109/ICMLA.2017.0-134
150+
.. |travis| image:: https://travis-ci.org/kk7nc/HDLTex.svg?branch=master
151+
:target: https://travis-ci.org/kk7nc/HDLTex
152+
.. |wercker status| image:: https://app.wercker.com/status/24a123448ba8764b257a1df242146b8e/s/master
153+
:target: https://app.wercker.com/project/byKey/24a123448ba8764b257a1df242146b8e
154+
.. |Join the chat at https://gitter.im/HDLTex| image:: https://badges.gitter.im/Join%20Chat.svg
155+
:target: https://gitter.im/HDLTex/Lobby?source=orgpage
156+
.. |appveyor| image:: https://ci.appveyor.com/api/projects/status/github/kk7nc/HDLTex?branch=master&svg=true
157+
:target: https://ci.appveyor.com/project/kk7nc/hdltex
158+
.. |arXiv| image:: https://img.shields.io/badge/arXiv-1709.08267-red.svg?style=flat
159+
:target: https://arxiv.org/abs/1709.08267
160+
.. |RG| image:: https://img.shields.io/badge/ResearchGate-HDLTex-blue.svg?style=flat
161+
:target: https://www.researchgate.net/publication/319968747_HDLTex_Hierarchical_Deep_Learning_for_Text_Classification
162+
.. |Binder| image:: https://mybinder.org/badge.svg
163+
:target: https://mybinder.org/v2/gh/kk7nc/HDLTex/master
164+
.. |license| image:: https://img.shields.io/github/license/mashape/apistatus.svg?maxAge=2592104
165+
:target: https://github.com/kk7nc/HDLTex/blob/master/LICENSE
166+
.. |Data| image:: https://img.shields.io/badge/DOI-10.17632/9rw3vkcfy4.6-blue.svg?style=flat
167+
:target: http://dx.doi.org/10.17632/9rw3vkcfy4.6
168+
.. |Pic| image:: http://kowsari.net/____impro/1/onewebmedia/HDLTex.png?etag=W%2F%22c90cd-59c4019b%22&sourceContentType=image%2Fpng&ignoreAspectRatio&resize=821%2B326&extract=0%2B0%2B821%2B325?raw=false
169+
:alt: HDLTex as both Hierarchy lavel are DNN
170+
.. |twitter| image:: https://img.shields.io/twitter/url/http/shields.io.svg?style=social
171+
:target: https://twitter.com/intent/tweet?text=HDLTex:%20Hierarchical%20Deep%20Learning%20for%20Text%20Classification%0aGitHub:&url=https://github.com/kk7nc/HDLTex&hashtags=DeepLearning,Text_Classification,classification,MachineLearning,deep_neural_networks
172+

0 commit comments

Comments
 (0)