Insurance and reinsurance companies often receivepaper-based applications and supporting documents from clients/policyholders,agents, and brokers. These contain data that must be rekeyed from the sourcedocuments for operational processing. Such data may be structured, semistructured (e.g.: loss reports, insurance contracts) or unstructured (e.g.:emails, property inspections), and it is typically either in PDF format (notalways “selectable”) and/or in Excel (not always correctly formatted). Forunderwriting, data for a rated entity may need to be extracted, identified, andaggregated from multiple forms or sources for the same submission.