Key points are not available for this paper at this time.
The abundance of the data in the Internet facilitates the improvement of and processing tools. The trend in the open data publishing the adoption of structured formats like CSV and RDF. However, there still a plethora of unstructured data on the Web which we assume contain. For this reason, we propose an approach to derive semantics from web which are still the most popular publishing tool on the Web. The paper discusses methods and services of unstructured data extraction and as well as machine learning techniques to enhance such a workflow. eventual result is a framework to process, publish and visualize linked data. The software enables tables extraction from various open data in the HTML format and an automatic export to the RDF format making the linked. The paper also gives the evaluation of machine learning techniques conjunction with string similarity functions to be applied in a tables task.
Galkin et al. (Mon,) studied this question.