Learning Bilingual Word Representations by Marginalizing Alignments

Tomás Kociský, Karl Moritz Hermann, Phil Blunsom

Abstract: We present a probabilistic model that simultaneously learns alignments and distributed representations for bilingual data. By marginalizing over word alignments the model captures a larger semantic context than prior work relying on hard alignments. The advantage of this approach is demonstrated in a cross-lingual classification task, where we outperform the prior published state of the art.