This repository contains keras implementation of the paper Learning Sentence Similarity with Siamese Recurrent Architectures link:http://www.mit.edu/~jonasm/info/MuellerThyagarajan_AAAI16.pdf
The data set is available at http://clic.cimec.unitn.it/composes/sick.html and also included in the repository. The SICK data set consists of about 10,000 English sentence pairs, generated starting from two existing sets: the 8K ImageFlickr data set and the SemEval 2012 STS MSR-Video Description data set.
The model uses GLoVe 6B 50D embeddings that can be downloaded from https://nlp.stanford.edu/projects/glove/
