Concept alignment of product taxonomies based on semantic similarity

The product taxonomy can provide knowledge support for many knowledge-based Web services. Merging different taxonomies is an effective way to build a complete product taxonomy. To achieve this goal, a core task is to align the concepts of different taxonomies. The traditional methods of conceptual alignment are insufficient in accuracy and efficiency. In this paper, we propose a new concept alignment by integrating three factors simultaneously: the concept's path semantic, topic similarity and dictionary-based semantic similarity. A series of experiments on real datasets show that the proposed method has a great improvement on the accuracy and efficiency of concept alignment.