Skip to content

Theano implementation of siamese LSTMs for evaluating semantic similarity between sentences.

Notifications You must be signed in to change notification settings

jonzarecki/LSTM-Sentence-Similarity

 
 

Repository files navigation

LSTM-Sentence-Similarity

Theano Implementation of "Siamese Recurrent Architectures for Learning Sentence Similarity".

Mueller, J and Thyagarajan, A. Siamese Recurrent Architectures for Learning Sentence Similarity. Proceedings of the 30th AAAI Conference on Artificial Intelligence (AAAI 2016). http://www.aaai.org/ocs/index.php/AAAI/AAAI16/paper/view/12195

Getting Started:

Download the word2vec model from https://code.google.com/archive/p/word2vec/ and download the file: GoogleNews-vectors-negative300.bin.gz and insert into data/word_embeddings

Use train_lstm.py in order to train a new lstm, use train_entailment.py to train an entailment classifier based on the already trained lstm mode. Other training methods exist in alternative_trains/

Technical Info

Python version 2.7 Tensorflow version 1.8 Gensim version 3.2

About

Theano implementation of siamese LSTMs for evaluating semantic similarity between sentences.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • OpenEdge ABL 99.6%
  • Python 0.4%