Translating Questions into Answers using DBPedia n-triples

TL;DR

This paper introduces a neural network-based question answering system that interprets questions using DBpedia n-triples and movie subtitle dialogues, showing promising results despite low automatic evaluation overlap.

Contribution

It presents a novel approach combining DBpedia n-triples and movie dialogues for training a question answering neural network.

Findings

Manual inspection shows promising answer quality

Low overlap in automatic evaluation suggests room for improvement

Combines structured data with natural language dialogues

Abstract

In this paper we present a question answering system using a neural network to interpret questions learned from the DBpedia repository. We train a sequence-to-sequence neural network model with n-triples extracted from the DBpedia Infobox Properties. Since these properties do not represent the natural language, we further used question-answer dialogues from movie subtitles. Although the automatic evaluation shows a low overlap of the generated answers compared to the gold standard set, a manual inspection of the showed promising outcomes from the experiment for further work.