Browsing Data Science Institute by Author "|~|1267880|~|"

Now showing items 1-12 of 12

    • Facilitating prediction of adverse drug reactions by using knowledge graphs and multi-label learning models 

      Muñoz, Emir; Nováček, Vít; Vandenbussche, Pierre-Yves (Oxford University Press (OUP), 2017-08-18)
      Timely identification of adverse drug reactions (ADRs) is highly important in the domains of public health and pharmacology. Early discovery of potential ADRs can limit their effect on patient lives and also make drug ...

    • A hybrid method for rating prediction using linked data features and text reviews 

      Yumusak, Semih; Muñoz, Emir; Minervini, Pasquale; Dogdu, Erdogan; Kodaz, Halife (CEUR-WS.org, 2016)
      This paper describes our entry for the Linked Data Mining Challenge 2016, which poses the problem of classifying music albums as good or bad by mining Linked Data. The original labels are assigned according to aggregated ...

    • Identifying equivalent relation paths in knowledge graphs 

      Mohamed, Sameh K.; Muñoz, Emir; Nováček, Vít; Vandenbussche, Pierre-Yves (Springer Verlag, 2017-06-19)
      Relation paths are sequences of relations with inverse that allow for complete exploration of knowledge graphs in a two-way unconstrained manner. They are powerful enough to encode complex relationships between entities ...

    • Learning content patterns from linked data 

      Muñoz, Emir (CEUR-WS.org, 2014)
      Linked Data (LD) datasets (e.g., DBpedia, Freebase) are used in many knowledge extraction tasks due to the high variety of domains they cover. Unfortunately, many of these datasets do not provide a description for their ...

    • A linked data-based decision tree classifier to review movies 

      Aldarra, Suad; Muñoz, Emir (CEUR-WS.org, 2015)
      In this paper, we describe our contribution to the 2015 Linked Data Mining Challenge. The proposed task is concerned with the prediction of review of movies as good or bad , as does Metacritic website based on critics ...

    • Mining cardinalities from knowledge bases 

      Muñoz, Emir; Nickles, Matthias (Springer Verlag, 2017-08-01)
      Cardinality is an important structural aspect of data that has not received enough attention in the context of RDF knowledge bases (KBs). Information about cardinalities can be useful for data users and knowledge engineers ...

    • On learnability of constraints from RDF data 

      Muñoz, Emir (Springer International Publishing, 2016-05-14)
      RDF is structured, dynamic, and schemaless data, which enables a big deal of flexibility for Linked Data to be available in an open environment such as the Web. However, for RDF data, flexibility turns out to be the source ...

    • Regularizing knowledge graph embeddings via equivalence and inversion axioms 

      Minervini, Pasquale; Costabello, Luca; Muñoz, Emir; Nováček, Vít; Vandenbussche, Pierre-Yves (Springer Verlag, 2017-12-30)
      Learning embeddings of entities and relations using neural architectures is an effective method of performing statistical learning on large-scale relational data, such as knowledge graphs. In this paper, we consider the ...

    • SemanTex: semantic text exploration using document links implied by conceptual networks extracted from the texts 

      Aldarra, Suad; Muñoz, Emir; Vandenbussche, Pierre-Yves; Nováček, Vít (ACMCEUR-WS.org, 2014)
      Despite of advances in digital document processing, exploration of implicit relationships within large amounts of textual resources can still be daunting. This is partly due to the ‘black-box’ nature of most current ...

    • Soft cardinality constraints on XML data: How exceptions prove the business rule 

      Ferrarotti, Flavio; Hartmann, Sven; Link, Sebastian; Marin, Mauricio; Muñoz, Emir (Springer Verlag, 2013)
      We introduce soft cardinality constraints which need to be satisfied on average only, and thus permit violations in a controlled manner. Starting from a highly expressive but intractable class, we establish a fragment that ...

    • Using drug similarities for discovery of possible adverse reactions 

      Muñoz, Emir; Nováček, Vít; Vandenbussche, Pierre-Yves (AMIA, 2017-02-10)
      We propose a new computational method for discovery of possible adverse drug reactions. The method consists of two key steps. First we use openly available resources to semi-automatically compile a consolidated data set ...

    • µRaptor: A DOM-based system with appetite for hCard elements 

      Muñoz, Emir; Costabello, Luca; Vandenbussche, Pierre-Yves (CEUR-WS.org, 2014)
      This paper describes µRaptor, a DOM-based method to extract hCard microformats from HTML pages stripped of microformat markup. µRaptor extracts DOM sub-trees, converts them into rules, and uses them to extract hCard ...