A Relaxed Matching Procedure for Unsupervised BLI
This work addresses the challenge of inducing bilingual lexicons without parallel corpora, which is incremental as it builds on an existing iterative framework.
The paper tackled the problem of unsupervised Bilingual Lexicon Induction (BLI) by proposing a relaxed matching procedure to improve translation pairings, resulting in substantial outperformance over previous unsupervised methods on standard benchmarks.
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.