Duality Regularization for Unsupervised Bilingual Lexicon Induction

TL;DR

This paper introduces a joint training approach with regularization for unsupervised bilingual lexicon induction, leveraging the duality between language pairs to improve translation accuracy.

Contribution

It proposes a novel joint primal-dual training framework with regularizers to enforce consistency, advancing unsupervised bilingual lexicon induction methods.

Findings

Significant performance improvements over baselines

Achieved best results on standard benchmarks

Effective across multiple language pairs

Abstract

Unsupervised bilingual lexicon induction naturally exhibits duality, which results from symmetry in back-translation. For example, EN-IT and IT-EN induction can be mutually primal and dual problems. Current state-of-the-art methods, however, consider the two tasks independently. In this paper, we propose to train primal and dual models jointly, using regularizers to encourage consistency in back translation cycles. Experiments across 6 language pairs show that the proposed method significantly outperforms competitive baselines, obtaining the best-published results on a standard benchmark.