Learning Translations via Matrix Completion

TL;DR

This paper introduces a matrix completion approach for bilingual lexicon induction, effectively leveraging bilingual and monolingual signals to improve translation learning without parallel corpora.

Contribution

It presents a novel matrix completion framework that integrates diverse signals, achieving state-of-the-art results in bilingual lexicon induction for various resource levels.

Findings

Achieves state-of-the-art performance in bilingual lexicon induction.

Effectively combines bilingual and monolingual signals.

Works well for both high-resource and low-resource languages.

Abstract

Bilingual Lexicon Induction is the task of learning word translations without bilingual parallel corpora. We model this task as a matrix completion problem, and present an effective and extendable framework for completing the matrix. This method harnesses diverse bilingual and monolingual signals, each of which may be incomplete or noisy. Our model achieves state-of-the-art performance for both high and low resource languages.