A computer system that can read scientific papers in a similar way to humans promises breakthroughs in cancer research, according to Cambridge scientists.
Called CRAB, the system is able to trawl through millions of peer-reviewed
articles for clues to the causes of tumours. Already, it has uncovered a
potential reason why some chemicals induce pancreatic cancer only in men.
CRAB 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
abiguities, 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," said Dr Anna Korhonen of the University of Cambridge, who
led the development of CRAB.
"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.
Emerging economies including China and India are producing scientific research
at an unprecedented rate, prompting fears that important discoveries could
be neglected my human readers.
"Although still under development, the system can be used to make connections that would be difficult to find, even if it had been possible to read all the documents," said Dr Korhonen.
CRAB is to be made available to researchers online via a web interface. It is hoped the technology can be adapted to other fields of science.
"Although still under development, the system can be used to make connections that would be difficult to find, even if it had been possible to read all the documents," said Dr Korhonen.
CRAB is to be made available to researchers online via a web interface. It is hoped the technology can be adapted to other fields of science.
No comments:
Post a Comment