← Search

Data · dataset · 2018

Leveraging Wikipedia Table Schemas for Knowledge Graph Augmentation

Listed in Borealis and Agri-environmental Research Data Dataverse — shown once because both records carry DOI 10.7939/dvn/f36tgc

General solutions to augment Knowledge Graphs (KGs) with facts extracted from Web tables aim to associate pairs of columns from the table with a KG relation based on the matches between pairs of entities in the table and facts in the KG.

Description

These approaches su er from intrinsic limitations due to the incompleteness of the KGs. In this paper we investigate an alternative solution, which lever- ages the patterns that occur on the schemas of a large corpus of Wikipedia tables.

Our experimental evaluation, which used DBpedia as reference KG, demonstrates the advantages of our approach over state-of-the-art solutions and reveals that we can extract more than 1.7M of facts with an estimated accuracy of 0.81 even from tables that do not expose any fact on the KG.

Links

Where it is published

Catalogue records · 1

Topics

Inferred from text
Artificial intelligence 72% · Tabular 65%
Provenance · 2 source records, 21 field assertions
SourceKeyLast seenRaw
Borealisdoi:10.7939/DVN/F36TGC13 d agoJSON v1
Agri-environmental Research Data Dataversedoi:10.7939/DVN/F36TGC11 d agoJSON v1
FieldAssertionExtractorEvidence
concepts[field].anzsrc:group:4602enrichment · borealisdata cataxonomy-embedding@1.0.0title+keywords+description (72%)
concepts[field].dataverse_subject:computer-and-information-sciencesource · borealisdata caconnector:borealisdata_ca@1.0.0/subjects
concepts[field].dataverse_subject:computer-and-information-sciencesource · borealisdata ca dataverseconnector:borealisdata_ca_dataverse@1.0.0/subjects
concepts[field].local:field:chemistrymapping · borealisdata ca dataverseconnector:borealisdata_ca_dataverse@1.0.0/subjects
concepts[field].local:field:computer-science-aimapping · borealisdata ca dataverseconnector:borealisdata_ca_dataverse@1.0.0/subjects
concepts[field].local:field:earth-environmentalmapping · borealisdata ca dataverseconnector:borealisdata_ca_dataverse@1.0.0/subjects
concepts[field].local:field:economics-financemapping · borealisdata ca dataverseconnector:borealisdata_ca_dataverse@1.0.0/subjects
concepts[field].local:field:engineeringmapping · borealisdata ca dataverseconnector:borealisdata_ca_dataverse@1.0.0/subjects
concepts[field].local:field:humanitiesmapping · borealisdata ca dataverseconnector:borealisdata_ca_dataverse@1.0.0/subjects
concepts[field].local:field:life-sciencesmapping · borealisdata ca dataverseconnector:borealisdata_ca_dataverse@1.0.0/subjects
concepts[field].local:field:mathematics-statisticsmapping · borealisdata ca dataverseconnector:borealisdata_ca_dataverse@1.0.0/subjects
concepts[field].local:field:medicine-healthmapping · borealisdata ca dataverseconnector:borealisdata_ca_dataverse@1.0.0/subjects
concepts[field].local:field:ocean-atmosphericmapping · borealisdata ca dataverseconnector:borealisdata_ca_dataverse@1.0.0/subjects
concepts[field].local:field:social-sciencemapping · borealisdata ca dataverseconnector:borealisdata_ca_dataverse@1.0.0/subjects
concepts[modality].local:modality:tabularenrichment · borealisdata cakeyword-concept-rules@1.0.0title+description (65%)
created_datesource · borealisdata caconnector:borealisdata_ca@1.0.0
descriptionsource · borealisdata caconnector:borealisdata_ca@1.0.0/description
publication_datesource · borealisdata caconnector:borealisdata_ca@1.0.0
titlesource · borealisdata caconnector:borealisdata_ca@1.0.0/name
updated_datesource · borealisdata caconnector:borealisdata_ca@1.0.0
version_labelsource · borealisdata caconnector:borealisdata_ca@1.0.0