CNN tensorflow text classification CNN文本分类的例子

from:http://deeplearning.lipingyang.org/tensorflow-examples-text/

TensorFlow examples (text-based)

This page provides links to text-based examples (including code and tutorial for most examples) using TensorFlow.

(Stay tuned, as I keep updating the post while I grow and plow in my deep learning garden:). Also, if you find a dead link, please email me –you can find my email address from the About page, which has a link to my academic website.)

Text summarization with TensorFlow (August 24, 2016 Google Research Blog) – GitHub repo
How to Run Text Summarization with TensorFlow (Oct 15, 2016)

This is a good post. It introduces how to train the model using your own dataset.

To create a useful model you should train it on a large dataset. Ideally, the dataset should be specific for your task. Summarizing news article may be different from summarizing legal documents or job descriptions.

TensorFlow — Text Classification (by Illia Polosukhin, Nov 19, 2016)

Full example can be found in TensorFlow examples (DNN-based text classification with DBpedia data): https://github.com/tensorflow/tensorflow/blob/master/tensorflow/examples/learn/text_classification.py (note, that code there will be updated with new APIs so it’s better to check out there).

Another text classification using CNN (CNN-based text classification with DBpedia data):

https://github.com/tensorflow/tensorflow/blob/master/tensorflow/examples/learn/text_classification_cnn.py

A TensorFlow Tutorial: Email Classification (Feb 1, 2016 by Josh Meyer)

It contains sample code for feeding customized training data set from csv files. It used a simple logistic regression classifier to classify Emails.

A nice tutorial on WildML that uses TensorFlow: Implementing a CNN for Text Classification in TensorFlow

Its code on GitHub: Convolutional Neural Network for Text Classification in Tensorflow (python 3) by dennybritz on Github (Python 2 version by atveit on Github, this one forked the python 3 version by dennybritz)

Note that python 3 version has more functionality (e.g., eval.py) and it is more up to date.

tf.device("/cpu:0") forces an operation to be executed on the CPU. By default TensorFlow will try to put the operation on the GPU if one is available, but the embedding implementation doesn’t currently have GPU support and throws an error if placed on the GPU.

RNNS IN TENSORFLOW, A PRACTICAL GUIDE AND UNDOCUMENTED FEATURES ( August 21, 2016) – github repo
In Sentiment Analysis setting, District Data Labs – Modern Methods for Sentiment Analysis talks about using word2vec.
See Paper: Effective Use of Word Order for Text Categorization with Convolutional Neural Networks , which goes into more technical details.

Johnson, R., & Zhang, T. (2014). Effective use of word order for text categorization with convolutional neural networks. arXiv preprint arXiv:1412.1058.