QA systems parse and transform natural language questions into logical forms to execute on the underlying Knowledge Bases. Searching and querying content that is both massive in scale and heterogeneous have become increasingly challenging since the heterogeneity of datasets impedes effective application of QA techniques. In fact, the heterogeneity of these datasets requires numerous integration steps before they can be used effectively in applications. The other main requirement for QA systems is completeness of the data, i.e., a complete coverage of the domain. ESR1 is working on addressing the problem of uniform access and on-the-fly integration for heterogeneous data sources that are required during QA. As a first step, ESR1 has assessed existing integration frameworks and quality assessment and enrichment approaches. Apart from this, he has collaborated with ESR2 on surveying existing Linked Data quality metrics. ESR1 has been working on Ontario, an approach for integrating heterogeneous data using a semantified data layer. In the reporting period, he has published three papers at international conferences and workshops. Also, he has participated at the 1st and 2nd WDAqua Learning Week as well as the 1st and 2nd R&D Week where he received technical and non-technical training and presented his research project and initial results from his research work.

Started:
2015-08-17
Supervisors:

Publications

Dataset reuse: An analysis of references in community discussions, publications and data. Endris, Kemele and Giménez-García, José M. and Thakkar, Harsh and Demidova, Elena and Zimmermann, Antoine and Lange, Christoph and Simperl, Elena. K-CAP 2017 PDF

MULDER: Querying the Linked Data Web by Bridging RDF Molecule Templates. Kemele M. Endris, Mikhail Galkin, Ioanna Lytra, Mohamed Nadjib Mami, Maria-Esther Vidal, Sören Auer. DEXA (1) 2017: 3-18 URL PDF

SMJoin: A Multi-way Join Operator for SPARQL queries. Galkin, Mikhail and Endris, Kemele and Acosta, Maribel and Collarana, Diego and Vidal, Maria-Esther and Auer, Sören. SEMANTiCS 2017 PDF

Are Linked Datasets fit for Open-domain Question Answering? A Quality Assessment. Harsh Thakkar, Kemele M. Endris, José M. Giménez-García, Jeremy Debattista, Christoph Lange, Sören Auer. WIMS 2016: 19:1-19:12 URL PDF

Question Answering on Linked Data: Challenges and Future Directions. Saeedeh Shekarpour, Denis Lukovnikov, Ashwini Jaya Kumar, Kemele Endris, Kuldeep Singh, Harsh Thakkar, Christoph Lange. Q4APS at WWW 2016: 693-698 URL PDF

Co-evolution of RDF Datasets. Sidra Faisal, Kemele M. Endris, Saeedeh Shekarpour, Sören Auer, Maria-Esther Vidal. ICWE 2016: 225-243 URL PDF