Exploring Sequence-to-Sequence Models for SPARQL Pattern Composition

TL;DR

This paper investigates the use of sequence-to-sequence neural models, called Neural SPARQL Machines, to convert natural language questions into complex SPARQL queries for improved question answering over knowledge bases.

Contribution

It demonstrates that sequence-to-sequence models are a promising approach for learning to compose SPARQL query patterns from natural language.

Findings

Sequence-to-sequence models effectively generate complex SPARQL queries.

Neural SPARQL Machines show potential for natural language question answering.

The approach simplifies translating natural language into formal queries.

Abstract

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.