SIENA: Semi-automatic semantic enhancement of datasets using concept recognition

摘要

The amount of data becoming available is rapidly increasing. Various research fields can benefit from the growing volume of information, including the biomedical domain. Unfortunately, answering a research question using the already available data usually requires information which can be found in more than one dataset. Moreover, the information needed is not only spread across sources, but also is stored in different formats such as comma-separated values (CSV), extensible markup language (XML) etc. Therefore data processing is usually needed to solve the provided task. However, data processing has been identified by 80% of data scientists as the most time consuming part of a project and at the same time, the least enjoyable one [1].