Nativeatom / Very-Deep-Convolutional-Networks-for-Natural-Language-Processing-in-tensorflow

implement the paper" Very Deep Convolutional Networks for Natural Language Processing"(https://arxiv.org/abs/1606.01781 ) in tensorflow

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Very-Deep-Convolutional-Networks-for-Natural-Language-Processing-in-tensorflow

Implement the paper" Very Deep Convolutional Networks for Natural Language Processing"(https://arxiv.org/abs/1606.01781) in tensorflow,just 9 layers.

Parts of code are based on https://github.com/amygdala/tensorflow-workshop/tree/master/workshop_sections/cnn_text_classification ,which is based on the https://github.com/dennybritz/cnn-text-classification-tf, and other parts are based on https://github.com/scharmchi/char-level-cnn-tf

The data of the experiment is dbpedia, the paper reports that the accuracy is 0.9865.

About

implement the paper" Very Deep Convolutional Networks for Natural Language Processing"(https://arxiv.org/abs/1606.01781 ) in tensorflow


Languages

Language:Jupyter Notebook 100.0%