Paper: Unsupervised Syntactic Alignment with Inversion Transduction Grammars

ACL ID N10-1014
Title Unsupervised Syntactic Alignment with Inversion Transduction Grammars
Venue Human Language Technologies
Session Main Conference
Year 2010
Authors

Syntactic machine translation systems cur- rently use word alignments to infer syntactic correspondences between the source and tar- get languages. Instead, we propose an un- supervised ITG alignment model that directly aligns syntactic structures. Our model aligns spans in a source sentence to nodes in a target parse tree. We show that our model produces syntactically consistent analyses where possi- ble, while being robust in the face of syntactic divergence. Alignment quality and end-to-end translation experiments demonstrate that this consistency yields higher quality alignments than our baseline.