Learning to Rank Query Graphs for Complex Question Answering over Knowledge Graphs
This work addresses the challenge of complex question answering for users of knowledge graphs, but it is incremental as it builds on existing neural ranking approaches.
The paper tackles the problem of ranking query graphs for complex question answering over knowledge graphs by proposing a self-attention based slot matching model that exploits query graph structure, which generally outperforms other models on two DBpedia datasets and shows substantial improvements through transfer learning to offset training data scarcity.
In this paper, we conduct an empirical investigation of neural query graph ranking approaches for the task of complex question answering over knowledge graphs. We experiment with six different ranking models and propose a novel self-attention based slot matching model which exploits the inherent structure of query graphs, our logical form of choice. Our proposed model generally outperforms the other models on two QA datasets over the DBpedia knowledge graph, evaluated in different settings. In addition, we show that transfer learning from the larger of those QA datasets to the smaller dataset yields substantial improvements, effectively offsetting the general lack of training data.