Tuesday, October 04, 2011

Advances in text analysis

Meaning-Based Computing: Text Analysis Takes a Great Leap Forward by Terence K. Huwe, Information Today (Sept / OCt 2011)

Meaning-based computing (MBC) is finally getting its due.

"MBC unites the power of modern search protocols with recent advances in text pattern recognition, language-context analysis, and even “sentiment analysis”— which sounds somewhat mysterious. The cumulative advances in MBC are enabling computers to make far more useful inferences about the meaning of communications, even as language usage evolves. Although MBC has been used over the past 8 years with considerable success, the synergy of recent advances has gained wider attention. "

MBC will aid, not supplant, the creation and use of taxonomies for access.

"Taxonomy: It will still matter. The contemporary web is a matrix of artifacts and living documents that have their own “social life,” as Xerox Palo Alto Research Center’s John Seely Brown famously said in the book, The Social Life of Information, which he co-authored with Paul Duguid. HTML5 and the semantic web will add embedded functionalities that further support the development of taxonomies, ontologies, and crowdsourcing techniques to tag useful resources. Meaning-based computing will not supplant these features, although it will likely introduce powerful new ways to look inside document wrappers and parse the evolving meaning of everyday language. If so, then MBC presents digital content managers with another new opportunity to improve access and retrieval. "

0 comments: