Any Suggestions? Active Schema Support for Structuring Web Information

TitleAny Suggestions? Active Schema Support for Structuring Web Information
Publication TypeConference Paper
Year of Publication2014
AuthorsHomoceanu, S., F. Geilert, C. Pek, and W. - T. Balke
Refereed DesignationUnknown
Conference Name19th International Conference on Database Systems for Advanced Applications (DASFAA)
Date Published04/2014
Conference LocationBali, Indonesia

Backed by major Web players, is the latest broad initiative for structuring Web information. Unfortunately, extensive analysis on a
large corpus of 733 million web documents shows that, a year after its introduction, only 1.56% of the documents had annotations. The reason is that the annotation process is quite demanding, hindering wide-spread adoption. State-of-the-art tools like Google’s Structured Data Markup Helper offer only limited support. In this paper we propose SASS, a system for automatically finding high quality schema suggestions for page content, to ease up the annotation process. For this purpose the system employs supervised machine learning techniques together with user feedback. Additional support for binding attributes to values reduces the effort even further. These features make SASS superior to other tools offering support for annotations up to date.



Full Text


DASFAA14_conference_105.pdf1.1 MB