Beyond Offline Mapping: Learning Cross Lingual Word Embeddings through Context Anchoring

Abstract

Recent research on cross-lingual word embeddings has been dominated by unsupervised mapping approaches that align monolingual embeddings. Such methods critically rely on those embeddings having a similar structure, but it was recently shown that the separate training in different languages causes departures from this assumption. In this paper, we propose an alternative approach that does not have this limitation, while requiring a weak seed dictionary (e.g., a list of identical words) as the only form of supervision. Rather than aligning two fixed embedding spaces, our method works by fixing the target language embeddings, and learning a new set of embeddings for the source language that are aligned with them. To that end, we use an extension of skip-gram that leverages translated context words as anchor points, and incorporates self-learning and iterative restarts to reduce the dependency on the initial dictionary. Our approach outperforms conventional mapping methods on bilingual lexicon induction, and obtains competitive results in the downstream XNLI task.

arXiv commentACL 2021

References in corpus (8)

• Distributed Representations of Words and Phrases and their Compositionality
• On the Cross-lingual Transferability of Monolingual Representations
• BilBOWA: Fast Bilingual Distributed Representations without Word Alignments
• Analyzing the Limitations of Cross-lingual Word Embedding Mappings
• Bilingual Lexicon Induction through Unsupervised Machine Translation
• Towards Optimal Transport with Global Invariances
• Learning Unsupervised Word Mapping by Maximizing Mean Discrepancy
• A Simple and Effective Approach to Robust Unsupervised Bilingual Dictionary Induction