SSE

SSE represents Shortcut-stacked Sentence Encoder Model, which was first proposed in this paper:

@InProceedings{nie-bansal:2017:RepEval,
 author    = {Nie, Yixin  and  Bansal, Mohit},
 title     = {Shortcut-Stacked Sentence Encoders for Multi-Domain Inference},
 booktitle = {Proceedings of the 2nd Workshop on Evaluating Vector Space Representations for NLP},
 year      = {2017}
}

A few notes

1. We refer the original Pytorch code for implementation.
2. Refer DecAtt model to download data and run commands.