Learning regular expressions for the extraction of product attributes from E-commerce microdata
Petar Petrovski, Volha Bryl, Christian Bizer · MADOC (University of Mannheim) · 2014
A large number of e-commerce websites have started tomarkup their products using standards such as Microdata, Microfor-mats, and RDFa. However, the markup is mostly not as fine-grainedas desirable for applications and mostly consists of free text properties.This paper discusses the challenges that arise in the task of matchingdescriptions of electronic products from several thousand e-shops thato↵er Microdata markup. Specifically, our goal is to extract product at-tributes from product o↵ers, by means of regular expressions, in order tobuild well structured product specifications. For this purpose we presenta technique for learning regular expressions. We evaluate our attributeextraction approach using 1.9 million product o↵ers from 9,240 e-shopswhich we extracted from the Common Crawl 2012, a large public Webcorpus. Our results show that with our approach we are able to reach asimilar matching quality as with manually defined regular expressions.