IBM has been working on intelligence systems that can pull subtext from stored data (including both structured information in databases and unstructured information such as e-mail or video files). IBM's OmniFind (IBM's enterprise search engine for file systems, content repositories, databases, collaboration systems, applications and intranets) integrates with any portal or content management system. IBM's natural language processing known as PIQUANT (for "the Practical Intelligent Question Answering Technology") analyzes the semantic structure of a passage, culling information that wasn't overtly present on a database or file system and allowing users to find answers to specific questions -- even if the keywords they use do not exist in the article they're searching. And IBM's WebFountain system converts the disparate ways information is presented online into a uniform format that can be analyzed. (John Battelle, a search expert and co-founder of Wired magazine, calls WebFountain and Google "kissing cousins," since they were both inspired by an earlier concept of a system that would count inbound and outbound links to identify central sites in a community.)
posted by Marcus Zillman |
4:10 AM
