Colorful figures connected by lines

Text analytics is the process of extracting information from unstructured text using text mining and natural language processing (NLP) algorithms. Mining unstructured data can be challenging, however, because natural language text is often inconsistent and ambiguous.

VISTA researchers are developing leading-edge systems to extract and index information found in large collections of scientific and technical literature. The goal is to create tools that facilitate access to knowledge in diverse fields, whether it be computational linguistics or biomedicine.