Abstract: Knowledge base question answering (KB-QA) has received extensive attention in recent years,and becomes an important natural language processing task.In the knowledge base question answering task,simple question refers to the question that can be answered by a single-fact of the knowledge base.For this task,the existing approaches mainly map the question and the KB fact into a common vector space and calculate their similarity to get the answer.But this approach would lose part of the semantic interaction information of the original words.To solve this problem,a multi-view attention-based relation detection approach was proposed,which aims to model the correlation between the question and the KB relation from multiple perspectives,and preserves more original interaction information so as to improve the accuracy of the approach.In addition,in order to alleviate the impacts of noisy data and improve the accuracy of entity recognition,this paper also encoded the question by combining the dynamic word vectors based on the language model and the part-of-speech feature of the word during the process of entity linking.Finally,experiments conducted on the SimpleQuestions dataset based on FB2M and FB5M achieve the accuracy results of 78.9% and 78.3%,respectively,which illustrative the effectiveness of the proposed approach for reflecting the semantic correlation between the question and the KB relation,and reflect the improvements of the accuracy for single-fact KBQA.

Key words: Attention mechanism, Deep learning, Knowledge base, Natural language processing, Question answering