A Relaxed Matching Procedure for Unsupervised BLI

Abstract

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.

arXiv comment6 pages,1 figures, accepted as short paper by ACL2020

References in corpus (7)

• Distributed Representations of Words and Phrases and their Compositionality
• Exploiting Similarities among Languages for Machine Translation
• Unsupervised Machine Translation Using Monolingual Corpora Only
• Unsupervised Hyperalignment for Multilingual Word Embeddings
• Bilingual Lexicon Induction through Unsupervised Machine Translation
• A Robust Self-Learning Method for Fully Unsupervised Cross-Lingual Mappings of Word Embeddings: Making the Method Robustly Reproducible as Well
• Wasserstein-Fisher-Rao Document Distance