CLMar 7, 2018

Translating Questions into Answers using DBPedia n-triples

arXiv:1803.02914v1
Originality Synthesis-oriented
AI Analysis

This is an incremental approach to improving question answering systems using structured and natural language data.

The paper tackled the problem of question answering by training a sequence-to-sequence neural network on DBpedia n-triples and movie subtitle dialogues, but automatic evaluation showed low overlap with gold standards while manual inspection indicated promising results for future work.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes