Under the Hood Updates For The Wolfram Alpha Computational Engine
At a first glance, the Wolfram Alpha website looks pretty much as it did when it first launched?with the straightforward input field. But inside that simple exterior an incredible amount has happened, according to its developer, Stephen Wolfram.
The development organization of Wolfram Alpha has been buzzing with activity all summer. The team has been working on the improvement of the engine's "knowledge" on more topics, as well as in the way the engine understands the what a user asks for every query. "Close to half the time that Wolfram Alpha doesn?t give a result, it?s not because it doesn?t have the necessary knowledge, or can?t do the necessary computation. It?s because it doesn?t understand what?s being asked, " Stephen Wolfram wrote at its blog.
Wolfram said that the engine has been enhanced by taking advantage of new techniques based on NKS. This would allow the engine understand the input queries - which are a based on a human language - more efficiently.
The results so far are quite encouraging, according to Wolfram. In just a couple of months, the development team reduced the "fall-through rate" of queries the engine does not understand by 10%.
Another fascinating thing about the Wolfram Alpha project is the way it mixes deep theoretical ideas with very practical implementation.
And one of the great achievements this summer has been streamlining the implementation. New data comes into Wolfram Alpha all the time. Despite the dificulties, the Wolfram Alpha team has managed to make the idea of one code update per week for Wolfram Alpha work.
Wolfram estimates that 10% and 15% completely new knowledge domains has been added to the engine since its launch.
In addition to new content, Wolfram's team has been working very hard on new delivery and interface mechanisms for Wolfram Alpha, which are expected to be announced soon.
"It?s been a great first summer for Wolfram Alpha. It was a mad dash to launch Wolfram Alpha when we did. But we?ve actually built up over the summer to an even greater development intensity, though now with a progressively larger team and increasingly streamlined development systems," Wolfram said..
"These are exciting times. The vision of Wolfram Alpha is really working! With every day bringing new advances. Progressively building up the largest coherent repository of human knowledge ever assembled," he added.
Wolfram said that the engine has been enhanced by taking advantage of new techniques based on NKS. This would allow the engine understand the input queries - which are a based on a human language - more efficiently.
The results so far are quite encouraging, according to Wolfram. In just a couple of months, the development team reduced the "fall-through rate" of queries the engine does not understand by 10%.
Another fascinating thing about the Wolfram Alpha project is the way it mixes deep theoretical ideas with very practical implementation.
And one of the great achievements this summer has been streamlining the implementation. New data comes into Wolfram Alpha all the time. Despite the dificulties, the Wolfram Alpha team has managed to make the idea of one code update per week for Wolfram Alpha work.
Wolfram estimates that 10% and 15% completely new knowledge domains has been added to the engine since its launch.
In addition to new content, Wolfram's team has been working very hard on new delivery and interface mechanisms for Wolfram Alpha, which are expected to be announced soon.
"It?s been a great first summer for Wolfram Alpha. It was a mad dash to launch Wolfram Alpha when we did. But we?ve actually built up over the summer to an even greater development intensity, though now with a progressively larger team and increasingly streamlined development systems," Wolfram said..
"These are exciting times. The vision of Wolfram Alpha is really working! With every day bringing new advances. Progressively building up the largest coherent repository of human knowledge ever assembled," he added.
