Papers by Ashwinkumar Ganesan
Learning a Reversible Embedding Mapping using Bi-Directional Manifold Alignment (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing models that perform unidirectional mappings are unipolar and unintended . |
| Approach: | They propose a bi-directional mapping algorithm that learns a non-linear mapping between two manifolds by explicitly training it to be bijective. |
| Outcome: | The proposed model reduces the number of models by 50% and improves performance over unidirectional translation models. |