Research & Innovation

Despite recent efforts to achieve a high level of interoperability of Machine Learning (ML) experiments, positively collaborating with the Reproducible Research context, we still run into problems created due to the existence of different ML platforms: each of those have a specific conceptualization or schema for representing data and metadata.

Knowledge graphs encode semantics that describes resources in terms of several aspects, e.g., neighbors, class hierarchies, or node degrees. Assessing relatedness of knowledge graph entities is crucial for several data-driven tasks, e.g., ranking, clustering, or link discovery. However, existing similarity measures consider aspects in isolation when determining entity relatedness.

The Semantic Web provides mechanisms to interlink data in a fast and efficient way and build complex information networks. However, one of the most important features missing for industrial application is version control which allows recording changes and rolling them back at any time if necessary.

Ignoring End-User License Agreements (EULAs) for online services due to their length and complexity is a risk undertaken by the majority of online and mobile service users. This paper presents an Ontology-Based Information Extraction (OBIE) method for EULA term and phrase extraction to facilitate a better understanding by humans.

In this paper, we present a multi-featured supervised automatic keyword extraction system. We extracted salient semantic features which are descriptive of candidate keyphrases, a Random Forest classifer was used for training. The system achieved an accuracy of 58.3 % precision and has shown to outperform two top performing systems when benchmarked on a crowdsourced dataset.

Many ranking methods have been proposed for RDF data. These methods often use the structure behind the data to measure its importance. Recently, some of these methods have started to explore information from other sources such as the Wikipedia page graph for better ranking RDF data. In this work, we propose DBtrends, a ranking function based on query logs.