A Study of URI Spotting for Question Answering over Linked Data (QALD)

Abstract : Recently, there have been studies on linked data-based question answering systems such as Question Answering over Linked Data (QALD). In these linked data-based question answering systems, it is essential to connect URI which is used as an identifier of the linked data with a chunk or surface form constituting such queries. This study attempts to suggest effective URI spotting that connects question-answering chunk and URI of the linked data using conventional natural language processing techniques. In addition, this study addresses a solution for selecting best linked data entities from chunk by using automatically generated standard RDF query language expression (SPARQL) queries.
Document type :
Conference papers
Complete list of metadatas

Cited literature [6 references]  Display  Hide  Download

https://hal.inria.fr/hal-01614981
Contributor : Hal Ifip <>
Submitted on : Wednesday, October 11, 2017 - 4:57:23 PM
Last modification on : Wednesday, October 11, 2017 - 5:00:35 PM
Long-term archiving on : Friday, January 12, 2018 - 3:40:53 PM

File

433802_1_En_17_Chapter.pdf
Files produced by the author(s)

Licence


Distributed under a Creative Commons Attribution 4.0 International License

Identifiers

Citation

Kyungtae Lim, Namkyoo Kang, Min-Woo Park. A Study of URI Spotting for Question Answering over Linked Data (QALD). 9th International Conference on Intelligent Information Processing (IIP), Nov 2016, Melbourne, VIC, Australia. pp.163-168, ⟨10.1007/978-3-319-48390-0_17⟩. ⟨hal-01614981⟩

Share

Metrics

Record views

41

Files downloads

77