CLSep 3, 2019

Duality Regularization for Unsupervised Bilingual Lexicon Induction

arXiv:1909.01013v22 citations
AI Analysis

This work addresses the challenge of inducing bilingual lexicons without parallel data, which is crucial for low-resource language translation, though it is incremental as it builds on existing back-translation symmetry.

The paper tackled the problem of unsupervised bilingual lexicon induction by leveraging the duality between language pairs, proposing joint training of primal and dual models with consistency regularizers. The method achieved state-of-the-art results, significantly outperforming baselines across 6 language pairs on a standard benchmark.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes