Semantic Textual Similarity (STS):

Dataset:

• Semantic Textual Similarity 2012-2017 Dataset
• The benchmark comprises 8628 sentence pairs. Each sentence pair is accompained with a similarity score (0-5), where 0 being least similar and 5 being most similar.
• The train-dev-test splits is as follows:

	train	dev	test	total
news	3299	500	500	4299
caption	2000	625	525	3250
forum	450	375	254	1079
total	5749	1500	1379	8628

Methodology:

• I have design a system similar to the one proposed in "Siamese Recurrent Architectures for Learning Sentence Similarity".
• Instead of a plain LSTM. I have used a BiLSTM followed by a dense layer.
• The loss used to exponential of the negative Manhattan distance between 2 sentence representations generated by the Siamese Network.
• The results can be further improved using the non-parametric log-linear classifier in the post-processing step as illustrated in the base paper.

Files:

• utils.py file contains all the helper funcitons.
• siamese_model.py contains the model architecture.
• main.ipynb contains the implementation.