Exploring Sequence-to-Sequence Models for SPARQL Pattern Composition
This addresses the challenge for lay users in accessing structured data through natural language, though it appears incremental as it explores existing architectures for a known bottleneck.
The paper tackles the problem of transforming complex natural language questions into SPARQL queries for knowledge bases, showing that sequence-to-sequence models are a viable and promising option for this task.
A booming amount of information is continuously added to the Internet as structured and unstructured data, feeding knowledge bases such as DBpedia and Wikidata with billions of statements describing millions of entities. The aim of Question Answering systems is to allow lay users to access such data using natural language without needing to write formal queries. However, users often submit questions that are complex and require a certain level of abstraction and reasoning to decompose them into basic graph patterns. In this short paper, we explore the use of architectures based on Neural Machine Translation called Neural SPARQL Machines to learn pattern compositions. We show that sequence-to-sequence models are a viable and promising option to transform long utterances into complex SPARQL queries.