Thursday 10th November, 2016
2:30pm to 3:15pm
DitaExchange has begun work using the Microsoft Azure Machine Learning offering and looking at ways of leveraging machine learning as it relates to content. Specifically, we are exploring (and seeing some very positive results) the areas of using predictive analytics of content to do things such as suggest items in content that would possibly need to be redacted if that content were to be made public, of using predefined data model ontologies to perform entity extraction from content (i.e., finding and pulling out a data record that’s ‘hidden’ within the content), and enhancing content by assessing its readability based on existing standards such as simplified technical English (STE). All of these efforts really focus on improving content value, accessibility and quality.
Sign in to add slides, notes or videos to this session