Annotation system for extracting attributes from electronic data structures

Abstract

Systems, methods, and other embodiments associated with extracting attributes from electronic data structures are described. In one embodiment, a method includes correlating tokens from description strings with defined attributes in an electronic inventory database by identifying which of the defined attributes match the tokens to link the tokens with columns of the database associated with the defined attributes. The method includes iteratively updating annotation strings for unidentified ones of the tokens by generating suggested matches for the unidentified tokens according to known correlations between identified tokens and the defined attributes using a conditional random fields model. The method also includes populating the database using the identified tokens from the description strings according to the annotation strings by automatically storing the tokens from the description strings into the columns as identified by the annotation strings.