Learning Bilingual Word Representations by Marginalizing Alignments
arXiv:1405.0947
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.
Proceedings of ACL 2014 (Short Papers)