SIFT: An Algorithm for Extracting Structural Information From Taxonomies

TL;DR

SIFT is a three-step algorithm designed to analyze and leverage the hierarchical structure of taxonomies to infer correspondences, especially useful when textual matching fails.

Contribution

The paper introduces SIFT, a novel structural analysis algorithm that enhances taxonomy merging by exploiting hierarchical information, independent of textual data.

Findings

Effective in scenarios where textual taxonomy alignment fails

Improves taxonomy merging accuracy using structural information

Applicable to various hierarchical data analysis tasks

Abstract

In this work we present SIFT, a 3-step algorithm for the analysis of the structural information represented by means of a taxonomy. The major advantage of this algorithm is the capability to leverage the information inherent to the hierarchical structures of taxonomies to infer correspondences which can allow to merge them in a later step. This method is particular relevant in scenarios where taxonomy alignment techniques exploiting textual information from taxonomy nodes cannot operate successfully.