Dependency-based Sentence Alignment for Multiple Document Summarization

In this paper, we describe a method of automatic sentence alignment for building extracts from abstracts in automatic summarization research. Our method is based on two steps. First, we introduce the “dependency tree path” (DTP). Next, we calculate the similarity between DTPs based on the ESK (Extended String Subsequence Kernel), which considers sequential patterns. By using these procedures, we can derive one-to-many or many-to-one correspondences among sentences. Experiments using different similarity measures show that DTP consistently improves the alignment accuracy and that ESK gives the best performance.