Learning Crosslingual Word Embeddings without Bilingual Corpora
This addresses the resource-intensive and polysemy-handling limitations in crosslingual NLP for researchers and practitioners, though it is incremental as it builds on prior embedding methods.
The paper tackles the problem of learning crosslingual word embeddings without bilingual corpora by using a high-coverage dictionary and an EM-style algorithm on monolingual data, achieving state-of-the-art performance on bilingual lexicon induction and competitive results on other tasks.
Crosslingual word embeddings represent lexical items from different languages in the same vector space, enabling transfer of NLP tools. However, previous attempts had expensive resource requirements, difficulty incorporating monolingual data or were unable to handle polysemy. We address these drawbacks in our method which takes advantage of a high coverage dictionary in an EM style training algorithm over monolingual corpora in two languages. Our model achieves state-of-the-art performance on bilingual lexicon induction task exceeding models using large bilingual corpora, and competitive results on the monolingual word similarity and cross-lingual document classification task.