Findings of the Association for Computational Linguistics

Learning a Reversible Embedding Mapping using Bi-Directional Manifold Alignment

Ashwinkumar Ganesan, Francis Ferraro, and Tim Oates

August 1, 2021

We propose a Bi-Directional Manifold Alignment (BDMA) that learns a non-linear mapping between two manifolds by explicitly training it to be bijective. We demonstrate BDMA by training a model for a pair of languages rather than individual, directed source and target combinations, reducing the number of models by 50%. We show that models trained with BDMA in the “forward” (source to target) direction can successfully map words in the “reverse” (target to source) direction, yielding equivalent (or better) performance to standard unidirectional translation models where the source and target language is flipped. We also show how BDMA reduces the overall size of the model.

BibTeX OWL Tweet Scholar

Tags: learning, manifold, natural language processing

Type: InProceedings

Publisher: Association for Computational Linguistics

Note: Image from the paper:

Downloads: 416 downloads