Template-based question answering over RDF data

TLDR

As RDF data increasingly appears as Linked Data, intuitive access methods are needed; question‑answering systems translate natural language into triples matched against RDF, but triples often fail to capture the semantic structure of questions, limiting expressive query answering. The authors aim to overcome this limitation by generating a SPARQL template that mirrors the question’s internal structure. They produce the template from a parse of the question and instantiate it with statistical entity identification and predicate detection. Experiments show the approach is competitive and can answer questions that other methods cannot.

Abstract

As an increasing amount of RDF data is published as Linked Data, intuitive ways of accessing this data become more and more important. Question answering approaches have been proposed as a good compromise between intuitiveness and expressivity. Most question answering systems translate questions into triples which are matched against the RDF data to retrieve an answer, typically relying on some similarity metric. However, in many cases, triples do not represent a faithful representation of the semantic structure of the natural language question, with the result that more expressive queries can not be answered. To circumvent this problem, we present a novel approach that relies on a parse of the question to produce a SPARQL template that directly mirrors the internal structure of the question. This template is then instantiated using statistical entity identification and predicate detection. We show that this approach is competitive and discuss cases of questions that can be answered with our approach but not with competing approaches.