System and method for retrieving and intelligently grouping definitions found in a repository of documents

摘要

A system and method for retrieving and intelligently grouping definitions with common semantic meaning is disclosed. In response to a user's textual query for the definition of a term or phrase, a set of documents is retrieved from a repository of structured documents. The retrieved documents are labeled with a prediction score based upon predetermined glossary characteristics of the documents. In order to determine whether the retrieved documents are likely to be definitions, features commonly found in definitions are identified. The identified features are classified with numeric values and weighed using a support vector regression algorithm. Definitions that fail to meet a predetermined threshold score are discarded, and those that exceed a predetermined threshold score are labeled and stored in the local database.