Complex logical reasoning is a fundamental task in knowledge graph,which is to deduce the target entities from anchor entities and relations in query.However,previous approaches haven't considered relevance among sim-ilar queries that can be helpful for inference.This paper designs homogeneous query revisor,a flexible component which can be added to current approaches without changing their structure and improve the performance of complex query answering based on the features of similar queries.The revisor can bridge the distance between query embed-ding and answer embedding in each reasoning step.The performance of this revisor on different data sets is 1.6％-3.3％higher than that of the baseline models,which demonstrates the flexibility and effectiveness of our approach.
维普
万方数据