Enhancing SPARQL Query Performance With Recurrent Neural Networks

DBpedia is one of the most resourceful link databases today, and users need to use query syntax (e.g., SPARQL) to access information in DBpedia databases. However, not all users know SPARQL, so a natural language query system can be used to translate the user’s query into the corresponding syntax. Generating query syntax through the query system is both time-consuming and expensive. To improve the efficiency of query syntax generation from user questions, the multi-label template approach, specifically Light-QAwizard, is utilized. Light-QAwizard transforms the problem into one or more single-label classifications using multi-label learning template approaches. By implementing Light-QAwizard, query costs can be reduced by 50%, but it introduces a new label during the transformation process leading to sample imbalance, compromised accuracy, and limited scalability. To overcome these limitations, this paper employs two multi-label learning methods, Binary Relevance (BR) and Classifier Chains (CC), for question transformation. By employing Recurrent Neural Networks (RNNs) as a multi-label classifier for generating RDF (Resource Description Framework) triples, all the labels are predicted to align with the query intentions. To better account for the relationship between RDF triples, BR is integrated into an ensemble learning approach to result in the Ensemble BR. Experimental results demonstrate that our proposed method outperforms previous research in terms of improving query accuracy. The favorable experiments substantiate that the Ensemble BR or CC model demonstrates competitiveness by integrating label relationships into the trained model.