Learning Crosslingual Word Embeddings without Bilingual Corpora
TL
TL;DR
This method takes advantage of a high coverage dictionary in an EM style training algorithm over monolingual corpora in two languages to achieve 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.
Abstract
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.
References33 items
1
Swivel: Improving Embeddings by Noticing What's Missing
2
Bilingual Word Embeddings from Non-Parallel Document-Aligned Data Applied to Bilingual Lexicon Induction
3
Low Resource Dependency Parsing: Cross-lingual Parameter Sharing in a Neural Network Parser
4
Bilingual Word Representations with Monolingual Quality in Mind
5