Learning Translations via Matrix Completion

Derry Wijaya, Brendan Callahan, John Hewitt, Jie Gao, Xiao Ling +2 more
6/19/2024
cs.CL

No confident code implementation found for this paper.

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.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

How Lexical is Bilingual Lexicon Induction?

83% match2024

Semi-Supervised Learning for Bilingual Lexicon Induction

83% match1 repo52024

On Bilingual Lexicon Induction with Large Language Models

80% match1 repo122023

Bilex Rx: Lexical Data Augmentation for Massively Multilingual Machine Translation

80% match2023

Syntax as a Rosetta Stone: Universal Dependencies for In-Context Coptic Translation

80% match2026

Phrase-Based & Neural Unsupervised Machine Translation

79% match1 repo1.5k2018

Cite this paper

@article{wijaya2024learning,
  title  = {Learning Translations via Matrix Completion},
  author = {Derry Wijaya and Brendan Callahan and John Hewitt and Jie Gao and Xiao Ling and Marianna Apidianaki and Chris Callison-Burch},
  year   = {2024},
  eprint = {2406.13195},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2406.13195v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2406.13195.svg)](https://codeofpaper.com/paper/2406.13195)

Discussion