Data

Tools

Indexes

Applications

Experiments

Open Source Science

https://github.com/cahya-wirawan/cnn-for-sentence-classification-in-keras

Convolutional Neural Networks for Sentence Classification in Keras

https://github.com/cahya-wirawan/cnn-for-sentence-classification-in-keras

Science Score: 10.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ○
    CITATION.cff file
  • ○
    codemeta.json file
  • ○
    .zenodo.json file
  • ○
    DOI references
  • ✓
    Academic publication links
    Links to: arxiv.org
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (5.1%) to scientific vocabulary
Last synced: 10 months ago · JSON representation

Repository

Convolutional Neural Networks for Sentence Classification in Keras

Basic Info
  • Host: GitHub
  • Owner: cahya-wirawan
  • License: mit
  • Language: Python
  • Default Branch: master
  • Size: 6.22 MB
Statistics
  • Stars: 0
  • Watchers: 2
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Fork of alexander-rakhlin/CNN-for-Sentence-Classification-in-Keras
Created over 7 years ago · Last pushed almost 8 years ago

https://github.com/cahya-wirawan/CNN-for-Sentence-Classification-in-Keras/blob/master/ 

# Convolutional Neural Networks for Sentence Classification

Train convolutional network for sentiment analysis. Based on "Convolutional Neural Networks for Sentence Classification" by Yoon Kim, [link](http://arxiv.org/pdf/1408.5882v2.pdf). Inspired by Denny Britz article "Implementing a CNN for Text Classification in TensorFlow", [link](http://www.wildml.com/2015/12/implementing-a-cnn-for-text-classification-in-tensorflow/).
For "CNN-rand" and "CNN-non-static" gets to 88-90%, and "CNN-static" - 85%

## Some difference from original article:
* larger IMDB corpus, longer sentences; sentence length is very important, just like data size
* smaller embedding dimension, 20 instead of 300
* 2 filter sizes instead of original 3
* much fewer filters; experiments show that 3-10 is enough; original work uses 100
* random initialization is no worse than word2vec init on IMDB corpus
* sliding Max Pooling instead of original Global Pooling

## Dependencies

* The [Keras](http://keras.io/) Deep Learning library and most recent [Theano](http://deeplearning.net/software/theano/install.html#install) backend should be installed. You can use pip for that. 
Not tested with TensorFlow, but should work.

Owner

  • Name: Cahya Wirawan
  • Login: cahya-wirawan
  • Kind: user
  • Location: Vienna, Austria

System engineer, currently working on NLP, CV and Speech Recognition for fun and curiosity

GitHub Events

Total
Last Year