A computer system that can read scientific papers in way similar to humans might provide breakthroughs in the field of cancer research, scientists have revealed. The new system is called CRAB.
According to researchers from Cambridge University, CRAB is able to trawl through millions of peer-reviewed articles for clues to the causes of tumours, and it has already uncovered a potential reason why some chemicals induce pancreatic cancer only in men.
The system is the latest implementation of a rapidly emerging form of artificial intelligence called natural language processing, which is also used in the Siri personal assistant software in the iPhone 4S.
It allows computers to read texts and derive meaning from them, despite their complexity and ambiguities, as humans do.
The system will first be used to assess the risk that new chemicals could cause cancer.
"The first stage of any risk assessment is a literature review. It's a major bottleneck," the Telegraph quoted Anna Korhonen, who led the development of CRAB as saying.
"There could be tens of thousands of articles for a single chemical. Performed manually, it's expensive and, because of the rising number of publications, it's becoming too challenging to manage," she said.
CRAB is to be made available to researchers online via a web interface, and it is hoped that the technology can be adapted to other fields of science as well.