The use of semantic information found in structured knowledge bases has become an integral part of the processing pipeline of modern intelligent in- formation systems. However, such semantic information is frequently insuffi-cient to capture the rich semantics demanded by the applications, and thus cor-pus-based methods employing natural language processing techniques are often used conjointly to provide additional information. However, the semantic expres-siveness and interaction of these data sources with respect to query processing result quality is often not clear. Therefore, in this paper, we introduce the notion of relational purity which represents how well the explicitly modelled relation-ships between two entities in a structured knowledge base capture the implicit (and usually more diverse) semantics found in corpus-based word embeddings. The purity score gives valuable insights into the completeness of a knowledge base, but also into the expected quality of complex semantic queries relying on reasoning over relationships, as for example analogy queries.@en

Backed up by major Web players schema.org is the latest broad initiative for structuring Web information. Unfortunately, a representative analysis on a corpus of 733 million Web documents shows that, a year after its introduction, only 1.56% of documents featured any schema.org annotations. A probable reason is that providing annotations is quite tiresome, hindering wide-spread adoption. Here even 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 the annotation process. SASS intelligently blends supervised machine learning techniques with simple user feedback. Moreover, additional support features for binding attributes to values even further reduces the necessary effort. We show that SASS is superior to current tools for schema.org annotations.@en