Treo: Combining Entity-Search, Spreading Activation and Semantic Relatedness for Querying Linked Data (bibtex)
by André Freitas, João Gabriel de Oliveira, Sean O'Riain, Edward Curry, João Carlos Pereira da Silva
Abstract:
This paper describes Treo, a natural language query mecha- nismfor Linked Data which focuses on the provision of a precise and scalable semantic matching approach between natural language queries and distributed heterogeneous Linked Datasets. Treo's semantic matching approach combines three key elements: entity search, a Wikipedia-based semantic relatedness measure and spreading activation search. While entity search allows Treo to cope with queries over high volume and distributed data, the combination of entity search and spreading activation search using a Wikipedia-based semantic relatedness measure provides a flexible approach for handling the semantic match between natural language queries and Linked Data. Experimental results using the DBPedia QALD training query set showed that this combination represents a promising line of investigation, achieving a mean reciprocal rank of 0.489, precision of 0.395 and recall of 0.451.
Reference:
André Freitas, João Gabriel de Oliveira, Sean O'Riain, Edward Curry, João Carlos Pereira da Silva, "Treo: Combining Entity-Search, Spreading Activation and Semantic Relatedness for Querying Linked Data", In 1st Workshop on Question Answering over Linked Data (QALD-1), pp. 1-14, 2011.
Bibtex Entry:
@inproceedings{Freitas2011c,
abstract = {This paper describes Treo, a natural language query mecha- nismfor Linked Data which focuses on the provision of a precise and scalable semantic matching approach between natural language queries and distributed heterogeneous Linked Datasets. Treo's semantic matching approach combines three key elements: entity search, a Wikipedia-based semantic relatedness measure and spreading activation search. While entity search allows Treo to cope with queries over high volume and distributed data, the combination of entity search and spreading activation search using a Wikipedia-based semantic relatedness measure provides a flexible approach for handling the semantic match between natural language queries and Linked Data. Experimental results using the DBPedia QALD training query set showed that this combination represents a promising line of investigation, achieving a mean reciprocal rank of 0.489, precision of 0.395 and recall of 0.451.},
author = {Freitas, Andr{\'{e}} and {Gabriel de Oliveira}, Jo{\~{a}}o and O'Riain, Sean and Curry, Edward and {Carlos Pereira da Silva}, Jo{\~{a}}o},
booktitle = {1st Workshop on Question Answering over Linked Data (QALD-1)},
file = {:Users/ed/Library/Application Support/Mendeley Desktop/Downloaded/Freitas et al. - 2011 - Treo Combining Entity-Search, Spreading Activation and Semantic Relatedness for Querying Linked Data.pdf:pdf},
keywords = {LEIdataspace,Linked Data,Natural Language Queries,Treo},
mendeley-tags = {LEIdataspace},
pages = {1--14},
title = {{Treo: Combining Entity-Search, Spreading Activation and Semantic Relatedness for Querying Linked Data}},
url = {http://www.edwardcurry.org/publications/Freitas_QALD_2011.pdf},
year = {2011}
}
Powered by bibtexbrowser