An Evolutionary Algorithm to Learn SPARQL Queries for Source-Target-Pairs: Finding Patterns for Human Associations in DBpedia

TL;DR

This paper introduces an evolutionary algorithm that learns SPARQL query patterns from source-target pairs, enabling the discovery of human association patterns in DBpedia and assisting users in formulating effective queries.

Contribution

The work presents a novel evolutionary algorithm capable of learning and visualizing SPARQL query patterns from data, scalable to large datasets, and useful for predicting human associations.

Findings

Successfully learned patterns for human associations in DBpedia

Achieved MAP of 39.9% and Recall@10 of 63.9% in predictions

Scalable to datasets with over 7.9 billion triples

Abstract

Efficient usage of the knowledge provided by the Linked Data community is often hindered by the need for domain experts to formulate the right SPARQL queries to answer questions. For new questions they have to decide which datasets are suitable and in which terminology and modelling style to phrase the SPARQL query. In this work we present an evolutionary algorithm to help with this challenging task. Given a training list of source-target node-pair examples our algorithm can learn patterns (SPARQL queries) from a SPARQL endpoint. The learned patterns can be visualised to form the basis for further investigation, or they can be used to predict target nodes for new source nodes. Amongst others, we apply our algorithm to a dataset of several hundred human associations (such as "circle - square") to find patterns for them in DBpedia. We show the scalability of the algorithm by running it against a SPARQL endpoint loaded with > 7.9 billion triples. Further, we use the resulting SPARQL queries to mimic human associations with a Mean Average Precision (MAP) of 39.9 % and a Recall@10 of 63.9 %.