New science publications are appearing almost as fast as the digital data that is being created. MEDLINE – the US National Library of Medicine’s biomedical bibliographic database – now lists over 19 million records and adds up to 4,000 new records daily. With that kind of number, it quickly becomes unmanageable for scientists.

The University of Cambridge brought this to our attention in their article, “Mining the language of science.” How could a computer in this day and age be useful in this situation? It would need to be able to index and sort literature the way a scientist would. Enter semantic technology to help with text mining. One of the current challenges is to develop adaptive technology that can be ported easily between different text types, tasks and scientific fields. With this kind of technology developing, semantics continue to prove their worth.

Melody K. Smith

Sponsored by Data Harmony, a unit of Access Innovations, the world leader in indexing and making content findable.