Paper: Learning Non-Isomorphic Tree Mappings For Machine Translation

ACL ID P03-2041
Title Learning Non-Isomorphic Tree Mappings For Machine Translation
Venue Annual Meeting of the Association of Computational Linguistics
Session System Demonstration
Year 2003
Authors

Often one may wish to learn a tree-to-tree mapping, training it on unaligned pairs of trees, or on a mixture of trees and strings. Unlike previous statistical formalisms (limited to isomorphic trees), synchronous TSG allows local distortion of the tree topol- ogy. We reformulate it to permit dependency trees, and sketch EM/Viterbi algorithms for alignment, training, and decoding.