TensorFlow - Text Classification using Neural Networks

text-classification tensorflow
Sumit Chawla picture Sumit Chawla · Nov 14, 2015 · Viewed 13k times · Source

Is there any example on how can TensorFlow be used for text classification using neural networks?

Answer

ilblackdragon picture ilblackdragon · Nov 26, 2015

I've started putting together a set of examples for text classification on DBPedia dataset (predicting class of object from its description) as part of examples for Scikit Flow: https://github.com/tensorflow/tensorflow/blob/master/tensorflow/examples/learn/text_classification.py

Going to expand this example and write a blog post when will have enough different models showcased. Feel free to suggest other datasets and models you would be interested to see.

Related questions

Multilabel Text Classification using TensorFlow

The text data is organized as vector with 20,000 elements, like [2, 1, 0, 0, 5, ...., 0]. i-th element indicates the frequency of the i-th word in a text. The ground truth label data is also represented as vector with 4,000 elements, like [0, 0, 1, 0, 1, ...., 0]. i-th element indicates whether the …

Read More
Prevent over-fitting of text classification using Word embedding with LSTM

Objective : Identifying class label using user entered question (like Question Answer system). Data extracted from Big PDF file, and need to predict page number based on user input. Majorly used in policy document, where user have question about policy and …

Read More
How can I plot a confusion matrix?

I am using scikit-learn for classification of text documents(22000) to 100 classes. I use scikit-learn's confusion matrix method for computing the confusion matrix. model1 = LogisticRegression() model1 = model1.fit(matrix, labels) pred = model1.predict(test_matrix) cm=metrics.confusion_matrix(test_labels,…

Read More