Distributional-Relational Models: Scalable Semantics for Databases (bibtex)
by Andre Freitas, Siegfried Handschuh, Edward Curry
Abstract:
The crisp/brittle semantic model behind databases lim- its the scale in which data consumers can query, ex- plore, integrate and process structured data. Approaches aiming to provide more comprehensive semantic mod- els for databases, which are purely logic-based (e.g. as in Semantic Web databases) have major scalability lim- itations in the acquisition of structured semantic and commonsense data. This work describes a complemen- tary semantic model for databases which has seman- tic approximation at its center. This model uses distri- butional semantic models (DSMs) to extend structured data semantics. DSMs support the automatic construc- tion of semantic and commonsense models from large- scale unstructured text and provides a simple model to analyze similarities in the structured data. The combi- nation of distributional and structured data semantics provides a simple and promising solution to address the challenges associated with the interaction and process- ing of structured data.
Reference:
Andre Freitas, Siegfried Handschuh, Edward Curry, "Distributional-Relational Models: Scalable Semantics for Databases", In AAAI Spring Symposium Series (SSS-15), 2015.
Bibtex Entry:
@inproceedings{Freitas2015b,
abstract = {The crisp/brittle semantic model behind databases lim- its the scale in which data consumers can query, ex- plore, integrate and process structured data. Approaches aiming to provide more comprehensive semantic mod- els for databases, which are purely logic-based (e.g. as in Semantic Web databases) have major scalability lim- itations in the acquisition of structured semantic and commonsense data. This work describes a complemen- tary semantic model for databases which has seman- tic approximation at its center. This model uses distri- butional semantic models (DSMs) to extend structured data semantics. DSMs support the automatic construc- tion of semantic and commonsense models from large- scale unstructured text and provides a simple model to analyze similarities in the structured data. The combi- nation of distributional and structured data semantics provides a simple and promising solution to address the challenges associated with the interaction and process- ing of structured data.},
author = {Freitas, Andre and Handschuh, Siegfried and Curry, Edward},
booktitle = {AAAI Spring Symposium Series (SSS-15)},
file = {:Users/ed/Library/Application Support/Mendeley Desktop/Downloaded/Freitas, Handschuh, Curry - 2015 - Distributional-Relational Models Scalable Semantics for Databases.pdf:pdf},
title = {{Distributional-Relational Models: Scalable Semantics for Databases}},
url = {http://www.edwardcurry.org/publications/Freitas_AAAI15.pdf},
year = {2015}
}
Powered by bibtexbrowser