Abstract
The article presents a textual Big Data analytics solution developed in a real setting as a part of a high-capacity document digitization and storage system. A software based on machine learning techniques performs automated extraction and processing of textual contents. The work focuses on performance and data confidence evaluation and describes the approach to computing a set of indicators for textual data quality. It then presents experimental results.
Full Text
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call