Towards Multi-modal Entity Resolution for Product Matching
GI-Workshop on Foundations of Databases / Grundlagen von Datenbanken (GVDB 21)
Entity Resolution has been applied successfully to match product offers from different web shops. Unfortunately, in certain domains the (textual or numerical) attributes of a product are not sufficient for a reliable match decision. To overcome this problem we extend an attribute-based match- ing system to incorporate image data, which are available in almost every web shop. To evaluate the system we enhance the WDC product matching dataset with images crawled from the web. First evaluations show that the use of images is beneficial to increase recall and overall match quality.