Neural Relation Prediction for Simple Question Answering over Knowledge Graph
This work addresses relation prediction for factoid question answering, offering an incremental improvement over existing neural methods.
The paper tackles relation extraction for simple question answering over knowledge graphs by proposing an instance-based method that matches paraphrases of questions to predict relations, achieving better accuracy than state-of-the-art models on the SimpleQuestions dataset.
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.