Multilingual training of crosslingual word embeddings

Abstract

Crosslingual word embeddings represent lexical items from different languages using the same vector space, enabling crosslingual transfer. Most prior work constructs embeddings for a pair of languages, with English on one side. We investigate methods for building high quality crosslingual word embeddings for many languages in a unified vector space. In this way, we can exploit and combine information from many languages. We report competitive performance on bilingual lexicon induction, monolingual similarity and crosslingual document classification tasks.