Last week, the global information company Reuters made an announcement about its Calais metadata generation web service. Calais is an open API available for commercial and non-commercial use, which they want to use to make all the world's content more accessible, interoperable and valuable:
“Using natural language processing, machine learning and other methods, Calais categorizes and links your document with entities (people, places, organizations, etc.), facts (person ‘x’ works for company ‘y’), and events (person ‘z’ was appointed chairman of company ‘y’ on date ‘x’).”
Calais is a product of Reuters' acquisition last year of tagging platform vendor ClearForest Ltd, and many people question why they took a half-million high-end enterprise software and made it free! AOL Search and AltaVista veteran Gerry Campbell who moved to Reuters about a year and a half ago as president of Reuters Search and Content Technologies group, explains to Jennifer Zaino of SemanticWeb.com: "we made what used to be a half-million or quarter-million dollar, high-end deployment of enterprise software available for free, with the idea that the more folks use it the better Reuters can associate that content back in, so our customers can see more of what is going on in the world."
What Calais does for developers is that when called via a SAOP or a REST-based service with plain text or XML documents, it sends a response of the text analysis in RDF format. Currently, the response is tuned towards business-related people and events, and it supports "only" English language.
The next step for EuropeanStartups.com is to find a way to best implement Calais into its existing platform. That will be the third step of our development process towards the Semantic Web integration. You can follow the progress of the EuropeanStartups Semantic Web Project here.
“Using natural language processing, machine learning and other methods, Calais categorizes and links your document with entities (people, places, organizations, etc.), facts (person ‘x’ works for company ‘y’), and events (person ‘z’ was appointed chairman of company ‘y’ on date ‘x’).”
Calais is a product of Reuters' acquisition last year of tagging platform vendor ClearForest Ltd, and many people question why they took a half-million high-end enterprise software and made it free! AOL Search and AltaVista veteran Gerry Campbell who moved to Reuters about a year and a half ago as president of Reuters Search and Content Technologies group, explains to Jennifer Zaino of SemanticWeb.com: "we made what used to be a half-million or quarter-million dollar, high-end deployment of enterprise software available for free, with the idea that the more folks use it the better Reuters can associate that content back in, so our customers can see more of what is going on in the world."
What Calais does for developers is that when called via a SAOP or a REST-based service with plain text or XML documents, it sends a response of the text analysis in RDF format. Currently, the response is tuned towards business-related people and events, and it supports "only" English language.
The next step for EuropeanStartups.com is to find a way to best implement Calais into its existing platform. That will be the third step of our development process towards the Semantic Web integration. You can follow the progress of the EuropeanStartups Semantic Web Project here.
