Research on the Knowledge Graph Complex Q&A Method Based on Query Graph Generate
In order to study the knowledge graph complex question answering technology and solve the problem that the accuracy of knowledge graph complex Q&A is not high,a knowledge graph complex Q&A model QGGNet based on neural network was proposed.The model used encoder-decoder model to generate abstract query Graph(AQG),and introduced Graph Transformer to learn the vector representation of AQG.The Attention Mechanism was used to aggregate neighbor node information to update the vector representation of the query graph,and Bert ranking model was introduced to sort and score all the generated query graphs.In order to verify the effectiveness of the proposed method,a comparative experiment was designed.The experimental results showed that the evaluation value of this model was better than other models,and the method based on query graph generation could produce competitive experimental results on two knowledge graph question answering(KGQA)datasets,and could be well applied to the field of knowledge graph complex Q&A.
万方数据
维普
