Bilingual Lexicon Induction for Low-Resource Languages using Graph Matching via Optimal Transport

Abstract

Bilingual lexicons form a critical component of various NLP applications, including unsupervised and semisupervised machine translation and crosslingual information retrieval. In this work, we improve bilingual lexicon induction performance across 32 diverse language pairs with a graph-matching method based on optimal transport. The method is especially strong with very low amounts of supervision.

Tasks

Reproductions