MAAM: A Morphology-Aware Alignment Model for UnsupervisedBilingual Lexicon Induction
Abstract
The task of unsupervised bilingual lexicon induction (UBLI) aims to induce word translations from monolingual corpora in two languages. Previous work has shown that morphological variation is an intractable challenge
for the UBLI task, where the induced translation in failure case is usually morphologically
related to the correct translation. To tackle this
challenge, we propose a morphology-aware
alignment model for the UBLI task. The proposed model aims to alleviate the adverse effect of morphological variation by introducing grammatical information learned by the
pre-trained denoising language model. Results
show that our approach can substantially outperform several state-of-the-art unsupervised
systems, and even achieves competitive performance compared to supervised methods.