Learning Bilingual Word Representations by Marginalizing Alignments

  title={Learning Bilingual Word Representations by Marginalizing Alignments},
  author={Tom{\'a}s Kocisk{\'y} and Karl Moritz Hermann and Phil Blunsom},
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. 
Highly Cited
This paper has 59 citations. REVIEW CITATIONS

4 Figures & Tables



Citations per Year

60 Citations

Semantic Scholar estimates that this publication has 60 citations based on the available data.

See our FAQ for additional information.