Natural language processing helps government data mining
New sources of information call for new sorting methods. According to Government Technology, federal agencies coping with large volumes of unstructured information can benefit from natural language processing. Tech expert Tom Deutsch described the process as helpful in identifying facts behind a piece of text information, including who created it and the details of those mentioned.
"The model today is we force people to learn the tools that then interpret the results,” Deutsch said, according to the news source. "One of the models going forward is that the tools should be able to understand the native expression of 'what is the cost,' 'who did this,' 'what is likely to happen' – those types of interrogating systems."
Deutsch, according to Government Technology, is in favor of agencies holding onto all available data rather than shaping information to fit into a structured storage solution. In his opinion, there is value in keeping unstructured data and letting systems such as text analytics determine its usage.
A MeriTalk survey released in May found that the government will soon have huge quantities of new data from which to draw insight. The firm found that 64 percent of agencies have increased their unstructured data stores in the past two years. The primary use of this data thus far has been increasing efficiency, with 59 percent of officials listing it as information's top advantage.