Word Embedding Transformation for Robust Unsupervised Bilingual Lexicon Induction

TL;DR

This paper introduces a transformation-based approach to improve unsupervised bilingual lexicon induction by increasing the isomorphism of embedding spaces through rotation and scaling, achieving better results especially on distant language pairs.

Contribution

The proposed method enhances UBLI by transforming embeddings to better align language spaces without supervision, outperforming existing methods on challenging language pairs.

Findings

Achieves competitive or superior performance on benchmark datasets.

Particularly effective on distant language pairs.

Does not require supervision or language pair-specific tuning.

Abstract

Great progress has been made in unsupervised bilingual lexicon induction (UBLI) by aligning the source and target word embeddings independently trained on monolingual corpora. The common assumption of most UBLI models is that the embedding spaces of two languages are approximately isomorphic. Therefore the performance is bound by the degree of isomorphism, especially on etymologically and typologically distant languages. To address this problem, we propose a transformation-based method to increase the isomorphism. Embeddings of two languages are made to match with each other by rotating and scaling. The method does not require any form of supervision and can be applied to any language pair. On a benchmark data set of bilingual lexicon induction, our approach can achieve competitive or superior performance compared to state-of-the-art methods, with particularly strong results being found on distant languages.