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

http://www.socher.org/index.php/Main/Semi-SupervisedRecursiveAutoencodersForPredictingSentimentDistributions

sancha/jrae Issues

How to run RAE on windows? DO we need to compile first?
Updated 7 years ago1
how to feed our own word embeddings to RAE?
Updated 9 years ago
Licence #2
Updated 9 years ago
duplicate code
Updated 9 years ago
RAEBuilder_test wrong
Updated 9 years ago
Reproduce the result in Socher 2011 using jrae
Updated 9 years ago
Question about an exception
Updated 10 years ago15
System requirements for training on a larger corpus
Updated 10 years ago
Converging Problem with FullRun
Closed 10 years ago2
wordmap.map should be rebuilt in each run
Updated 10 years ago1
Pretraining on unlabled+labled data
Updated 10 years ago1
Accuracy is lower than what is declared in the paper or am i missing something?
Closed 11 years ago6
Other UTF-8 Languages
Closed 11 years ago1
Why not sparse auto-encoder ?
Closed 11 years ago1
license
Closed 12 years ago9
Looks great, build instructions
Closed 12 years ago1