In this paper we address the problem of obtaining structured information about products in the form of attribute-value pairs by leveraging a combination of enterprise internal product descriptions and external data. Product descriptions are short text strings used internally within enterprises to describe a product. These strings usually comprise of the Brand name, name of the product, and its attributes like size, color, etc. Existing product data quality solutions provide us the capability to standardize and segment these descriptions into their composing attributes using domain specific rulesets. We provide techniques that can leverage the supervision provided by these existing rulesets for extracting missing values from other external text data sources accurately. We use a large real life data collection to demonstrate the effectiveness of our approach.