# A Relaxed Matching Procedure for Unsupervised BLI

arXiv: https://arxiv.org/abs/2010.07095 · HTML: https://mlsanity.com/paper/2010.07095/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Oct 2020.

## Built on by (most cited first, 8 of 8)

- [Hierarchical Multi-Marginal Optimal Transport for Network Alignment](https://mlsanity.com/paper/2310.04470/) (2023)
- [Wasserstein-Fisher-Rao Embedding: Logical Query Embeddings with Local Comparison and Global Transport](https://mlsanity.com/paper/2305.04034/) (2023)
- [Bilingual Lexicon Induction for Low-Resource Languages using Graph Matching via Optimal Transport](https://mlsanity.com/paper/2210.14378/) (2022)
- [Unbalanced Optimal Transport for Unbalanced Word Alignment](https://mlsanity.com/paper/2306.04116/) (2023)
- [Quantifying Lexical Semantic Shift via Unbalanced Optimal Transport](https://mlsanity.com/paper/2412.12569/) (2024)
- [On Bilingual Lexicon Induction with Large Language Models](https://mlsanity.com/paper/2310.13995/) (2023)
- [TokAlign++: Advancing Vocabulary Adaptation via Better Token Alignment](https://mlsanity.com/paper/2605.13429/) (2026)
- [A survey of neural-network-based methods utilising comparable data for finding translation equivalents](https://mlsanity.com/paper/2410.15144/) (2024)

## Abstract (arXiv)

Recently unsupervised Bilingual Lexicon Induction (BLI) without any parallel corpus has attracted much research interest. One of the crucial parts in methods for the BLI task is the matching procedure. Previous works impose a too strong constraint on the matching and lead to many counterintuitive translation pairings. Thus, We propose a relaxed matching procedure to find a more precise matching between two languages. We also find that aligning source and target language embedding space bidirectionally will bring significant improvement. We follow the previous iterative framework to conduct experiments. Results on standard benchmark demonstrate the effectiveness of our proposed method, which substantially outperforms previous unsupervised methods.