https://github.com/sancha/jrae
I re-implemented a semi-supervised recursive autoencoder in java. I think it is a pretty nice technique. Check it out! Or fork it
https://github.com/sancha/jrae
Last synced: 5 months ago
JSON representation
I re-implemented a semi-supervised recursive autoencoder in java. I think it is a pretty nice technique. Check it out! Or fork it
- Host: GitHub
- URL: https://github.com/sancha/jrae
- Owner: sancha
- Created: 2012-01-20T06:05:39.000Z (over 14 years ago)
- Default Branch: master
- Last Pushed: 2017-04-21T17:49:37.000Z (about 9 years ago)
- Last Synced: 2023-03-13T09:10:35.973Z (about 3 years ago)
- Language: Java
- Homepage: http://www.socher.org/index.php/Main/Semi-SupervisedRecursiveAutoencodersForPredictingSentimentDistributions
- Size: 88.1 MB
- Stars: 73
- Watchers: 15
- Forks: 41
- Open Issues: 10
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
- awesome-java - JRAE
README
# Java Recursive Autoencoder
jrae is a re-implemention of semi-supervised recursive autoencoder in java. This package also contains code to demonstrate its usage.
More details are available at
http://www.socher.org/index.php/Main/Semi-SupervisedRecursiveAutoencodersForPredictingSentimentDistributions
Also read http://colah.github.io/posts/2014-07-NLP-RNNs-Representations/ for a neat explanation on recursive deep representations.
In short, semi-supervised recursive autoencoder is a feature learning algorithm to learn an encoding for text data and that can then be used for performing classification. The jrae package is pretty comprehensive - it includes code for learning the features as well as for performing basic classification, and is parallelized to run on a multi-core machine.
The package includes a demo of movie review classification on which the algorithm attains state-of-art results. Please use rc3 for your experiments https://github.com/sancha/jrae/releases/tag/rc3, and use the master branch only for contributions. The master branch includes some unsupported code.
# Updates
* The core feature of the recursive autoencoder is to learn a representation of words and sentences. Google recently released a similar tool, you are encouraged to try out the word2vec project http://code.google.com/p/word2vec/
* Stanford has an official code package integrated into Stanford CoreNLP, please check http://nlp.stanford.edu/sentiment/code.html for updates.
# Dependencies
The RAE package requires the jblas package for supporting the linear algebra
operations. These requirements are included in the lib directory.
* jblas
* junit4
* log4j
* jmatio
Including the jblas jar file may not be sufficient. JBLAS requires either
LAPACK or ATLAS. Check out https://github.com/mikiobraun/jblas if you run
into trouble. If you are running ubuntu, do `sudo apt-get install
libgfortran3`.
# BUGS
If you encounter any bugs, please report it on github.
* Author: Sanjeev Satheesh
* Created: 2012 February 20
* Keywords: java, sentiment analysis, machine learning, nlp
* URL: