English

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

Computation and Language 2022-10-27 v1 Machine Learning

Abstract

Bilingual lexicons form a critical component of various natural language processing applications, including unsupervised and semisupervised machine translation and crosslingual information retrieval. We improve bilingual lexicon induction performance across 40 language pairs with a graph-matching method based on optimal transport. The method is especially strong with low amounts of supervision.

Keywords

Cite

@article{arxiv.2210.14378,
  title  = {Bilingual Lexicon Induction for Low-Resource Languages using Graph Matching via Optimal Transport},
  author = {Kelly Marchisio and Ali Saad-Eldin and Kevin Duh and Carey Priebe and Philipp Koehn},
  journal= {arXiv preprint arXiv:2210.14378},
  year   = {2022}
}

Comments

EMNLP 2022 Camera-Ready

R2 v1 2026-06-28T04:30:51.696Z