Learning non-isomorphic tree mappings for machine translation 论文

摘要

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 topology. We reformulate it to permit dependency trees, and sketch EM/Viterbi algorithms for alignment, training, and decoding.