Findings of the Association for Computational Linguistics

Learning a Reversible Embedding Mapping using Bi-Directional Manifold Alignment

, , and

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.


  • 266065 bytes

learning, manifold, natural language processing

InProceedings

Association for Computational Linguistics

Image from the paper:

Downloads: 33 downloads

UMBC ebiquity