Paper: Learning Bilingual Word Representations by Marginalizing Alignments

ACL ID P14-2037
Title Learning Bilingual Word Representations by Marginalizing Alignments
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2014
Authors

We present a probabilistic model that si- multaneously learns alignments and dis- tributed representations for bilingual data. By marginalizing over word alignments the model captures a larger semantic con- text than prior work relying on hard align- ments. The advantage of this approach is demonstrated in a cross-lingual classifica- tion task, where we outperform the prior published state of the art.