ISEdb.COM

Stephen Wolfram, creator of the popular Mathematica software, has recently announced that his company will soon be launching a search engine with the specific aim to answer all factual questions, and that it will be able to do so thanks to breakthroughs in the field of natural language processing.

To be launched in May, Wolfram Alpha is intended to do for search what Mathematica did for math software. The application is designed to synthesize large amounts of data on the Web and organize it into an onthology in order to answer a vast amount of factual questions, “computing” the answer rather than looking it up on a database.

While Google can currently be used to answer factual questions, it is unable to do so by providing a direct answer to its users, instead yielding a very large number of web pages that are thought to be able to answer the user’s question, or simply contain the combination of words typed by the user in his query.

Wolfram Alpha, instead, aims to answer directly the user’s questions. “Fifty years ago, when computers were young, people assumed that they’d quickly be able to handle all these kinds of things… and that one would be able to ask a computer any factual question and have it compute the answer [...] a few years ago, I realised that I was finally in a position to try and do it,” Wolfram wrote in a blog post on his company’s website.

According to Wolfam, the system can understand questions that user enter in the search box, performs natural language processing to put the question in a form that is understandable by the underlying algorithms, and then computes the answer with its complex mathematical and scientific engine, which is based on the Mathematica symbol manipulation code.

Natural language processing is a complex field of artificial intelligence that attempts to parse human language and make it somehow “understandable” by a computer algorithm. The task is extremely difficult, and very little progress so far has been made in this field.

In his blog post, Wolfram claims his team managed to achieve natural language processing thanks to unprecedented breakthroughs in the field. Many are skeptical about such claims, but according to Nova Spivack, the founder of the Twine web service, Alpha is far more impressive than any other product in the market.

“Wolfram Alpha is like plugging into a vast electronic brain,” he wrote. “It provides extremely impressive and thorough questions asked in many different ways, and it computes answers – it doesn’t merely look them up in a big database”. According to Spivack, Wolfram Alpha may be as “important for the Web (and the world) as Google, but for a different purpose”.

As Spivack noted, in fact, the search engine could never realistically compete with Google, since it can only answer factual questions and it is therefore unable to answer requests for more information on a topic or evaluate and compare different products, which many Internet users find useful. Still, if successful Alpha could become a great tool for students and researchers looking for immediate answers without wasting time trying to find the right query and the right web page that satisfies their criteria.

“You would probably not use Wolfram Alpha to shop for a new car, find blog posts about a topic, or to choose a resort for your honeymoon–there is still no substitute for manual human-guided search for that. Where it appears to excel is when you want facts about something, or when you need to compute a factual answer to some set of questions about factual data,” Spivak continued, adding that while Wolfram’s engine isn’t going to replace Google, Google might like to own it.

Wolfram’s announcement has gathered wide media attention so far, but the 49-year-old is used to getting noticed for his exploits. After studying at Eton and Oxford, he went on to receive his PhD in theoretical physics from the California Institute of Technology at the age of 20 before being internationally recognized for his reasearch.