Aiming to Learn as We Do, a Machine Teaches ItselfBy STEVE LOHR
Published: October 4, 2010
Give a computer a task that can be crisply defined — win at chess, predict the weather — and the machine bests humans nearly every time. Yet when problems are nuanced or ambiguous, or require combining varied sources of information, computers are no match for human intelligence.
Few challenges in computing loom larger than unraveling semantics, understanding the meaning of language. One reason is that the meaning of words and phrases hinges not only on their context, but also on background knowledge that humans learn over years, day after day.
Since the start of the year, a team of researchers at Carnegie Mellon University — supported by grants from the Defense Advanced Research Projects Agency and Google, and tapping into a research supercomputing cluster provided by Yahoo — has been fine-tuning a computer system that is trying to master semantics by learning more like a human. Its beating hardware heart is a sleek, silver-gray computer — calculating 24 hours a day, seven days a week — that resides in a basement computer center at the university, in Pittsburgh. The computer was primed by the researchers with some basic knowledge in various categories and set loose on the Web with a mission to teach itself.
“For all the advances in computer science, we still don’t have a computer that can learn as humans do, cumulatively, over the long term,” said the team’s leader, Tom M. Mitchell, a computer scientist and chairman of the machine learning department.
The Never-Ending Language Learning system, or NELL, has made an impressive showing so far. NELL scans hundreds of millions of Web pages for text patterns that it uses to learn facts, 390,000 to date, with an estimated accuracy of 87 percent. These facts are grouped into semantic categories — cities, companies, sports teams, actors, universities, plants and 274 others. The category facts are things like “San Francisco is a city” and “sunflower is a plant.”
Leia mais...
Você pode navegar pelo banco de "fatos" do Nell em seu site oficial:
http://rtw.ml.cmu.edu/rtw/É espantoso quanta coisa ele aprendeu sozinho, mas o Nell ainda está longe de ser infalível. Uma curiosidade, por exemplo, é que ele tem 93,8 % de certeza de que a capital do Brasil é Curitiba
Nosso computador também é agnóstico, ele diz que tem poucas evidências para tirar qualquer conclusão sobre Deus, mas sabe que ele tem alguma relação com religião e organizações terroristas
Tópico: Computador aprende linguagem lendo a web (Lida 1446 vezes)