Share This Author
Using linked data to mine RDF from wikipedia's tables
This work uses an existing Linked Data knowledge-base to find pre-existing relations between entities in Wikipedia tables, suggesting the same relations as holding for other entities in analogous columns on different rows, and extracts RDF triples from Wikipedia's tables at a raw precision of 40%.
Regularizing Knowledge Graph Embeddings via Equivalence and Inversion Axioms
- Pasquale Minervini, Luca Costabello, Emir Muñoz, V. Novácek, P. Vandenbussche
- Computer ScienceECML/PKDD
- 18 September 2017
A principled and scalable method for leveraging equivalence and inversion axioms during the learning process, by imposing a set of model-dependent soft constraints on the predicate embeddings, which consistently improves the predictive accuracy of several neural knowledge graph embedding models without compromising their scalability properties.
Learning Content Patterns from Linked Data
- Emir Muñoz
- Computer ScienceLD4IE@ISWC
- 20 October 2014
This work presents an unsupervised approach to discover syntactic patterns in the properties used in LD datasets, and produces a content patterns database generated from the textual data (content) of properties, which describes the syntactic structures that each property have.
Facilitating prediction of adverse drug reactions by using knowledge graphs and multi‐label learning models
A specific way of using knowledge graphs to generate different feature sets and favourable performance of selected off‐the‐shelf multi‐label learning models in comparison with existing works are presented.
Accurate prediction of kinase-substrate networks using knowledge graphs
LinkPhinder is a new approach to prediction of protein signalling networks based on kinase-substrate relationships that outperforms existing approaches and can lead to establishing a new niche of AI applications in computational biology.
Using Drug Similarities for Discovery of Possible Adverse Reactions
The authors' approach scored best in all widely used metrics like precision, recall or the ratio of relevant predictions present among the top ranked results, and was as much as 125.79% over the next best approach.
Loss Functions in Knowledge Graph Embedding Models
A thorough analysis of different loss functions that can help with the procedure of embedding learning, providing a reduction of the evaluation metric based error and suggesting a new loss for representing training error in KGE models.
Triplifying Wikipedia's Tables
This work proposes that existing knowledge-bases can be leveraged to semi-automatically extract high-quality facts (in the form of RDF triples) from tables embedded in Wikipedia articles (henceforth called "Wikitables").
Performance Analysis of Algorithms to Reason about XML Keys
It is shown that XML keys as those studied here have great potential for diverse areas such as schema design, query optimization, storage and updates, data exchange and integration, and to exemplify this potential, it is used to calculate non-redundant covers for sets of XML keys, and shown that these covers can significantly reduce the number of XML Keys against which XML documents must be validated.
DRETa: Extracting RDF from Wikitables
DRETa is presented: a tool that uses DBpedia as a reference knowledge-base to extract RDF triples from generic Wikipedia tables to exploit the integrated content of these tables.