Web services require XML formatted data. Human translation of business information from the rapidly expanding volume of documents to XML is labor-intensive and impractical. Computer programs can be built to extract domain-specific facts from web documents and convert them into an XML format. With a continual feed of web articles, such a system could be used to maintain an up-to-date XML knowledge base that could power web services for businesses. In this research, we build a system to automatically extract information from electronic international corporate financial reports, and translate this information into XML or XBRL (a well-known XML extension for accounting and financial data).
Vinjamur, Anil; Conlon, Sumali; Lukose, Susan; McCready, Tim; and Hale, Jason, "Automatic Extraction and Generation of XML Documents from Financial Reports" (2005). AMCIS 2005 Proceedings. 472.