Adding Meaning to Millions of Numbers

Semantic technology could keep numbers tied to the information that explains what they mean.

Out of context, a number can be a dangerous thing. In 1991, for example, NASA's $125 million Mars Climate Orbiter was destroyed because one team of engineers used imperial units of measurement while others relied on metric ones. Consequently, the spacecraft was ordered to orbit at a perilously low altitude, which caused it to burn up in the Martian atmosphere.

Credit: Technology Review

Similar number-related mix-ups occur all the time back on Earth, albeit with slightly less catastrophic consequences. True Engineering Technology, a startup based in Cambridge, MA, has now developed semantic technology that adds meaning to numerical data to help prevent such miscommunications from occurring.

Today the company is launching a website called Numberspace that lets users upload pieces of numerical data--the distance from New York to London in kilometers, for example (5,581). Once it is semantically tagged, the information can be shared without losing its meaning. Customers can also pay for a business version that stores their information on a private server.

To store a number in the system--creating what the company calls a "truenumber"--a user simply types a short phrase into a form on the website. For the example cited above, a user might type, "The distance from New York to London in kilometers is 5,581." True Engineering Technology's software then interprets the phrase, extracting the number 5,581 and the meaning conveyed by key words and phrases such as "New York," "London," and "distance." Users can also add notes and comments to the truenumber, such as how it was calculated and whether there are queries concerning its accuracy.

Story continues below

Allen Razdow, CEO of True Engineering Technology, believes the technology will interest businesses that rely on accurate numbers for important decisions, particularly engineering firms. For example, workers at an automotive plant might need to access the most recent emissions figures stored from a range of different electronic documents. By storing these figures as truenumbers, any worker could search for them online and find the latest, most accurate figure. The system could also automatically perform conversions from one unit to another and flag any potential mismatches and errors. Users can also paste truenumbers onto websites or into Microsoft Office documents, keeping them linked to the contextual data stored on the Web server.

Razdow sees the technology as part of the movement toward the semantic Web, which aims to let computers store the meaning of pieces of information as well as the information itself. "I think there are natural, practical evolutions of how information gets represented that get to be more semantic by degrees," Razdow says. Numbers, he argues, are a good place to start because people follow certain rules when speaking about them. For example, it's easy to train the system to recognize which units represent distances, and to throw up error alerts if the user types that a distance is "5,581 seconds."