DM-BLI: Dynamic Multiple Subspaces Alignment for Unsupervised Bilingual Lexicon Induction

Unsupervised bilingual lexicon induction (BLI) task aims to find word translations between languages and has achieved great success in similar language pairs. However, related works mostly rely on a single linear mapping for language alignment and fail on distant or lowresource language pairs, achieving less than half the performance observed in similar language pairs. In this paper, we introduce DM-BLI, a Dynamic Multiple subspaces alignment framework for unsupervised BLI. DM-BLI improves language alignment by utilizing multiple subspace alignments instead of a single mapping. We begin via unsupervised clustering to discover subspaces in source embedding space. Then we identify corresponding subspaces in the target space using a rough global alignment. DM-BLI further employs intra-cluster and inter-cluster contrastive learning to refine precise alignment for each subspace pair. Experiments conducted on standard BLI datasets for 12 language pairs (6 richresource and 6 low-resource) demonstrate substantial gains achieved by our framework. We release our code at https://github.com/huling-2/DM-BLI .git.