CLJun 19, 2024
Learning Translations via Matrix Completion
Derry Wijaya, Brendan Callahan, John Hewitt, Jie Gao, Xiao Ling, Marianna Apidianaki, Chris Callison-Burch
arXiv:2406.13195v11098 citations
Originality Highly original
AI Analysis
This addresses the problem of learning word translations without bilingual parallel corpora for NLP researchers and practitioners.
The paper tackles Bilingual Lexicon Induction by modeling it as a matrix completion problem, achieving state-of-the-art performance for both high and low resource languages.
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.