Multilingual Models for Compositional Distributed Semantics

Understand

We present a novel technique for learning semantic representations, which extends the distributional hypothesis to multilingual data and joint-space embeddings.

• Our models leverage parallel data and learn to strongly align the embeddings of semantically equivalent sentences, while maintaining sufficient distance between those of dissimilar sentences.
• The models do not rely on word alignments or any syntactic information and are successfully applied to a number of diverse languages.
• We extend our approach to learn semantic representations at the document level, too.