by André Freitas, João Gabriel Oliveira, Seán O'Riain, João C.P. da Silva, Edward Curry
Abstract:
Linked Data brings inherent challenges in the way users and applications consume the available data. Users consuming Linked Data on the Web, should be able to search and query data spread over potentially large numbers of heterogeneous, complex and distributed datasets. Ideally, a query mechanism for Linked Data should abstract users from the representation of data. This work focuses on the investigation of a vocabulary independent natural language query mechanism for Linked Data, using an approach based on the combination of entity search, a Wikipedia-based semantic relatedness measure and spreading activation. Wikipedia-based semantic relatedness measures address existing limitations of existing works which are based on similarity measures/term expansion based on WordNet. Experimental results using the query mechanism to answer 50 natural language queries over DBpedia achieved a mean reciprocal rank of 61.4%, an average precision of 48.7% and average recall of 57.2%.
Reference:
André Freitas, João Gabriel Oliveira, Seán O'Riain, João C.P. da Silva, Edward Curry, "Querying linked data graphs using semantic relatedness: A vocabulary independent approach", In Data & Knowledge Engineering, vol. 88, pp. 126-141, 2013.
Bibtex Entry:
@article{Freitas2013,
abstract = {Linked Data brings inherent challenges in the way users and applications consume the available data. Users consuming Linked Data on the Web, should be able to search and query data spread over potentially large numbers of heterogeneous, complex and distributed datasets. Ideally, a query mechanism for Linked Data should abstract users from the representation of data. This work focuses on the investigation of a vocabulary independent natural language query mechanism for Linked Data, using an approach based on the combination of entity search, a Wikipedia-based semantic relatedness measure and spreading activation. Wikipedia-based semantic relatedness measures address existing limitations of existing works which are based on similarity measures/term expansion based on WordNet. Experimental results using the query mechanism to answer 50 natural language queries over DBpedia achieved a mean reciprocal rank of 61.4%, an average precision of 48.7% and average recall of 57.2%.},
author = {Freitas, Andr{\'{e}} and Oliveira, Jo{\~{a}}o Gabriel and O'Riain, Se{\'{a}}n and da Silva, Jo{\~{a}}o C.P. and Curry, Edward},
doi = {10.1016/j.datak.2013.08.003},
file = {:Users/ed/Library/Application Support/Mendeley Desktop/Downloaded/Freitas et al. - 2013 - Querying linked data graphs using semantic relatedness A vocabulary independent approach.pdf:pdf},
issn = {0169023X},
journal = {Data & Knowledge Engineering},
keywords = {Linked data,Natural language queries,RDF,independent queries,semantic relatedness,vocabulary},
month = {nov},
pages = {126--141},
title = {{Querying linked data graphs using semantic relatedness: A vocabulary independent approach}},
url = {http://www.edwardcurry.org/publications/freitas_dke_2013.pdf},
volume = {88},
year = {2013}
}