Mapping Natural Language to Description Logic

Abstract : While much work on automated ontology enrichment has focused on mining text for concepts and relations, little attention has been paid to the task of enriching ontologies with complex axioms. In this paper, we focus on a form of text that is frequent in industry, namely system installation design principle (SIDP) and we present a framework which can be used both to map SIDPs to OWL DL axioms and to assess the quality of these automatically derived axioms. We present experimental results on a set of 960 SIDPs provided by Airbus which demonstrate (i) that the approach is robust (97.50% of the SIDPs can be parsed) and (ii) that DL axioms assigned to full parses are very likely to be correct in 96% of the cases.
Document type :
Conference papers
Complete list of metadatas

Cited literature [21 references]  Display  Hide  Download

https://hal.inria.fr/hal-01577655
Contributor : Bikash Gyawali <>
Submitted on : Monday, September 4, 2017 - 12:06:26 PM
Last modification on : Tuesday, December 18, 2018 - 4:38:02 PM

File

springer_ack.pdf
Files produced by the author(s)

Identifiers

Citation

Bikash Gyawali, Anastasia Shimorina, Claire Gardent, Samuel Cruz-Lara, Mariem Mahfoudh. Mapping Natural Language to Description Logic. ESWC 2017 - Extended Semantic Web Conference, May 2017, Portoroz, Slovenia. ⟨10.1007/978-3-319-58068-5_17⟩. ⟨hal-01577655v2⟩

Share

Metrics

Record views

324

Files downloads

1046