Outlining and Filling: Hierarchical Query Graph Generation for Answering Complex Questions Over Knowledge Graphs

Query graph construction aims to construct the correct executable SPARQL on the KG to answer natural language questions. Although recent methods have achieved good results using neural network-based query graph ranking, they suffer from three new challenges when handling more complex questions: 1) complicated SPARQL syntax, 2) huge search space, and 3) locally ambiguous query graphs. In this paper, we provide a new solution. As a preparation, we extend the query graph by treating each SPARQL clause as a subgraph consisting of vertices and edges and define a unified graph grammar called AQG to describe the structure of query graphs. Based on these concepts, we propose a novel end-to-end model that performs hierarchical autoregressive decoding to generate query graphs. The high-level decoding generates an AQG as a constraint to prune the search space and reduce the locally ambiguous query graph. The bottom-level decoding accomplishes the query graph construction by selecting appropriate instances from the preprepared candidates to fill the slots in the AQG. The experimental results show that our method greatly improves the SOTA performance on complex KGQA benchmarks. Equipped with pre-trained models, the performance of our method is further improved, achieving SOTA for all three datasets used.

Automated summary

Query graph construction aims to generate a correct SPARQL query to answer natural language questions on a knowledge graph. Existing methods face challenges in handling complex questions including complicated SPARQL syntax, huge search space, and locally ambiguous query graphs. This paper proposes a novel end-to-end approach that leverages a unified graph grammar called AQG and hierarchical autoregressive decoding to construct query graphs effectively. Experimental results demonstrate that the proposed method significantly improves the state-of-the-art performance on complex KGQA benchmarks.