Automatic analysis of semantic similarity in comparable text through syntactic tree matching

We propose to analyse semantic similarity in comparable text by matching syntactic trees and labeling the alignments according to one of five semantic similarity relations. We present a Memory-based Graph Matcher (MBGM) that performs both tasks simultaneously as a combination of exhaustive pairwise classification using a memory-based learner, followed by global optimization of the alignments using a combinatorial optimization algorithm. The method is evaluated on a monolingual treebank consisting of comparable Dutch news texts. Results show that it performs substantially above the baseline and close to the human reference.