Abstract: A system and method are provided for automatically generating a summary document with information mined from a data repository. The database stores information garnered from a plurality of sources. The information includes the type of data which can be easily organized into fields, as well as less definable data such as transcribed dictation. The information is converted into a markup language for parsing and storage as tagged data and marked up data objects. The summary document is created from the tagged and marked up data objects. Specific examples are also provided for the generation of a clinical resume type summary document.