Sya: Enabling spatial awareness inside probabilistic knowledge base construction

Ibrahim Sabek, Mohamed F. Mokbel

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Scopus citations

Abstract

This paper presents Sya; the first spatial probabilistic knowledge base construction system, based on Markov Logic Networks (MLN). Sya injects the awareness of spatial relationships inside the MLN grounding and inference phases, which are the pillars of the knowledge base construction process, and hence results in a better knowledge base output. In particular, Sya generates a probabilistic model that captures both logical and spatial correlations among knowledge base relations. Sya provides a simple spatial high-level language, a spatial variation of factor graph, a spatial rules-query translator, and a spatially-equipped statistical inference technique to infer the factual scores of relations. In addition, Sya provides an optimization that ensures scalable grounding and inference for large-scale knowledge bases. Experimental evidence, based on building two real knowledge bases with spatial nature, shows that Sya can achieve 70% higher F1-score on average over the state-of-the-art DeepDive system, while achieving at least 20% reduction in the execution times.

Original languageEnglish (US)
Title of host publicationProceedings - 2020 IEEE 36th International Conference on Data Engineering, ICDE 2020
PublisherIEEE Computer Society
Pages1177-1188
Number of pages12
ISBN (Electronic)9781728129037
DOIs
StatePublished - Apr 2020
Externally publishedYes
Event36th IEEE International Conference on Data Engineering, ICDE 2020 - Dallas, United States
Duration: Apr 20 2020Apr 24 2020

Publication series

NameProceedings - International Conference on Data Engineering
Volume2020-April
ISSN (Print)1084-4627

Conference

Conference36th IEEE International Conference on Data Engineering, ICDE 2020
CountryUnited States
CityDallas
Period4/20/204/24/20

Bibliographical note

Funding Information:
∗Also affiliated with University of Minnesota, MN, USA. 1This work is partially supported by the National Science Foundation, USA, under Grants IIS-1907855, IIS-1525953 and CNS-1512877.

Fingerprint Dive into the research topics of 'Sya: Enabling spatial awareness inside probabilistic knowledge base construction'. Together they form a unique fingerprint.

Cite this