Watch out, Google! Twine may tangle you up!
Technology Review is reporting today on a web application from Radar Technologies, named Twine, that uses The Semantic Web and natural language processing to index information in a new way. What makes this one different is that you can enter your own information such as emails, doc files, spreadsheet and other local files, and also web bookmarks and such, and have Twine make a coherent whole out of the whole mess. So if you’re looking for an elusive bit of how-to info you remember reading, but don’t remember if it was in an email, in a local document, or on the web, you can use Twine to find it.
According to the article, “In addition to employing the Semantic Web standards, Twine is also using extremely advanced machine learning and natural-language processing algorithms that give it capabilities beyond anything that relies on manual tagging. The tool uses a combination of natural-language algorithms to automatically extract key concepts from collections of text, essentially automatically tagging them. According to Spivack, these algorithms adroitly handle ambiguous sets of words, determining, for example, whether J.P. Morgan is a person or a company, depending on the context. And Twine can find the subject of a text even if a keyword is never mentioned, he says, by using statistical machine learning to compare the text with data sources such as Wikipedia. “We can determine when a document is about a subject even if the subject isn’t mentioned in the document,” Spivack says. “So we can add new paths and new ways to get to the document” during a search.”
This is one of the first applications to take advantage of the strengths of the Semantic Web, which uses standards developed by the W3. It’ll be interesting to see how well tables and tag soup get parsed by Twine.
Technorati Tags: Semantic Web, Twine, Search, Indexing Information
