An Automatic Approach for Mapping Product Taxonomies in E-Commerce Systems

The recent explosion of Web shops has made the user task of finding the desired products an increasingly difficult one. One way to solve this problem is to offer an integrated access to product information on the Web, for which an important component is the mapping of product taxonomies. In this paper, we introduce CMAP, an algorithm that can be used to map one product taxonomy to another product taxonomy. CMAP employs word sense disambiguation techniques and lexical and structural similarity measures in order to find the best matching categories. The performance on precision, recall, and the F1-measure is compared favourably with state-of-the-art algorithms for taxonomy mapping.