Supervised Mover's Distance: A simple model for sentence comparison
ParallelDots, Inc., Gurgaon, India
- Published
- Accepted
- Subject Areas
- Artificial Intelligence, Data Science, Natural Language and Speech
- Keywords
- Supervised Mover's Distance, Natural Language Inference, Sentence Comparison, Paraphrase Detection
- Copyright
- © 2018 Srivastava
- Licence
- This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, reproduction and adaptation in any medium and for any purpose provided that it is properly attributed. For attribution, the original author(s), title, publication source (PeerJ Preprints) and either DOI or URL of the article must be cited.
- Cite this article
- 2018. Supervised Mover's Distance: A simple model for sentence comparison. PeerJ Preprints 6:e26847v1 https://doi.org/10.7287/peerj.preprints.26847v1
Abstract
We propose a simple Neural Network model which can learn relation between sentences by modeling the task as Earth Mover's Distance(EMD) calculation. Underlying hypothesis is that a neural module can learn to approximate the flow optimization in EMD calculation for sentence comparison. Our model is simple to implement, light in terms of parameters and works across multiple supervised sentence comparison tasks. We show good results for the model on two datasets. Our model combines LSTM with a relational unit to model sentence comparison.
Author Comment
This is version 1 of my mini project to model sentence comparison.