Robin Blandford [ ByteSurgery.com ]

05/02/08 Irish Startups: Get Your hands on Reuters Calais

SINGAPORE - Reuters have released an open API called Calais.

The Calais web service automatically attaches rich semantic metadata to the content you submit – in well under a second. 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’). The metadata results are stored centrally and returned to you as industry-standard RDF constructs accompanied by a Globally Unique Identifier (GUID). Using the Calais GUID, any downstream consumer is able to retrieve this metadata via a simple call to Calais.

This comes from the recent acquisition of ClearForest. I’ve played with ClearForest’s Firefox plugin for a while now, and it’s seriously powerful. Recent meetings with them for the project I’m working on have been impressive too. There are big opportunities for some Irish startup’s here to jump on the semantic mark-up band wagon early, easily & economically. I’ve already some directly as it’s a perfect fit to their applications.

Reuters are offering a US$5,000 bounty going for the first person to create a WordPress plugin with the following specifications…

Here’s the basic concept: A highly configurable plugin for WordPress that enriches a blog with several capabilities

• Tag auto suggestion: Using the content of the blog entry the plugin will provide a list of suggested semantic tags. For example, if the post talks about company “a” buying company “b” the plugin would suggest “Acquisition”, “Company A” and “Company B” as potential tags
• Semantic cloud: We all love tag clouds and we’d like to take it a step further. The plugin should support the generation of a configurable semantic tag cloud of entities and facts derived from the blog’s content
• GUID Incorporation: The Calais web service returns a Globally Unique Identifier (GUID) for each document submitted. The plugin should modify the RSS feed for the site to incorporate the GUID in a TBD location.

Thanks to Andy Waite for the tip-off of the launch. Read a news article about Calais here.

-Robin.

(Image Credit: Swimming pool on the roof of the Pan Pacific Hotel, from the KL tower, Kuala Lumpur, Malaysia. By Author.)

Tags: calais, opencalais, semantic, tagging

Write Comment

Name (required)

Mail (will not be published) (required)

Website

Notify me of followup comments via e-mail

---

---