#CurEx: A System for Extracting, Curating, and Exploring Domain-Specific Knowledge Graphs from Text
- author:Michael Loster, Felix Naumann, Jan Ehmueller, Benjamin Feldmann
- abstract:The integration of diverse structured and unstructured informationsources into a unied, domain-specic knowledge base is an impor-tant task in many areas. A well-maintained knowledge base enablesdata analysis in complex scenarios, such as risk analysis in the -nancial sector or investigating large data leaks, such as the Paradiseor Panama papers. Both the creation of such knowledge bases, aswell as their continuous maintenance and curation involves manycomplex tasks and considerable manual eort.With CurEx, we present a modular system that allows struc-tured and unstructured data sources to be integrated into a domain-specic knowledge base. In particular, we (i) enable the incrementalimprovement of each individual integration component; (ii) enablethe selective generation of multiple knowledge graphs from theinformation contained in the knowledge base; and (iii) provide twodistinct user interfaces tailored to the needs of data engineers andend-users respectively. The former has curation capabilities andcontrols the integration process, whereas the latter focuses on theexploration of the generated knowledge graph.
- keywords: domain-specific knowledge base.interfaces tailored,knowledge graph
- interpretation:
- pdf: paper
- code:
- dataset:
- ppt/video:
- curator: Wu Bo