Neural Relation Prediction for Simple Question Answering over Knowledge Graph

TL;DR

This paper introduces an instance-based neural approach for relation prediction in simple question answering over knowledge graphs, focusing on paraphrase detection to improve accuracy.

Contribution

It presents a novel paraphrase-based method for relation prediction that outperforms existing neural models on the SimpleQuestions dataset.

Findings

Achieves higher accuracy than state-of-the-art models

Effective in capturing paraphrases sharing relation semantics

Improves relation extraction in simple QA tasks

Abstract

Knowledge graphs are widely used as a typical resource to provide answers to factoid questions. In simple question answering over knowledge graphs, relation extraction aims to predict the relation of a factoid question from a set of predefined relation types. Most recent methods take advantage of neural networks to match a question with all predefined relations. In this paper, we propose an instance-based method to capture the underlying relation of question and to this aim, we detect matching paraphrases of a new question which share the same relation, and their corresponding relation is selected as our prediction. The idea of our model roots in the fact that a relation can be expressed with various forms of questions while these forms share lexically or semantically similar terms and concepts. Our experiments on the SimpleQuestions dataset show that the proposed model achieves better accuracy compared to the state-of-the-art relation extraction models.