Extracting Financial Information from Text Documents

The majority of electronic data today is in textual form. Financial data such as articles in the Wall Street Journal are written as texts. These electronic documents contain a wealth of information but require human interpretation. For financial analysis, rapid up-to-date information is critical. Most software tools currently require data which are better structured than text (such as data in relational databases). Thus, our research goal is to build a system, “FIRST” (Flexible Information extRaction SysTem), that will extract data from financial articles and store the output in an explicit format. FIRST uses natural language processing techniques and resources such as the lexical database WordNet and collocation information to extract information. We hope to be able to extract data such as an organization’s name, its profit/loss status, and sales status, from financial articles to input into a database. The data will come from international corporate reports which appear in the Wall Street Journal.