Categorically speaking

Designed for such information-intense industries as pharmaceuticals, financial services and law firms, LexiQuest has released Categorize, a new product for automated document categorization and taxonomy management.

Powered by LexiQuest's language recognition technology, LexiQuest Categorize will help firms efficiently organize and manage hundreds of thousands of documents, improving knowledge management and information sharing.

The company claims LexiQuest Categorize is based on 24 years of research into computational linguistics and adapts to language the same way people do. Using a set of training documents, Categorize "reads" the content and "learns" the type of information you expect to see in each category. The company explains that the resulting definitions can then be customized and refined by expert users to ensure accuracy. Incoming documents are then read in the same manner and compared to category definitions until a suitable match is found, at which time the document will be assigned to that category.

LexiQuest says Categorize is capable of handling over 250,000 pages of text per hour and can work on almost any text format, including HTML, XML, MS Office, PDF and e-mail.