Two Way Adversarial Unsupervised Word Translation

TL;DR

This paper introduces a joint bidirectional adversarial approach for unsupervised word translation that enhances translation accuracy without requiring extensive supervision or seed dictionaries.

Contribution

It proposes a novel method that simultaneously learns translations in both directions, improving upon previous unsupervised translation techniques.

Findings

Achieves higher translation accuracy than previous methods

Operates effectively with minimal or no supervision

Successfully learns bidirectional word mappings

Abstract

Word translation is a problem in machine translation that seeks to build models that recover word level correspondence between languages. Recent approaches to this problem have shown that word translation models can learned with very small seeding dictionaries, and even without any starting supervision. In this paper we propose a method to jointly find translations between a pair of languages. Not only does our method learn translations in both directions but it improves accuracy of those translations over past methods.