Exploiting Hybrid Semantics of Relation Paths for Multi-hop Question Answering Over Knowledge Graphs
This addresses the problem of complex question answering for users needing accurate information from knowledge graphs, with incremental improvements in leveraging relation path semantics.
The paper tackled the challenge of multi-hop question answering over knowledge graphs by exploiting hybrid semantics of relation paths, achieving superior performance on three datasets, especially in multi-hop scenarios.
Answering natural language questions on knowledge graphs (KGQA) remains a great challenge in terms of understanding complex questions via multi-hop reasoning. Previous efforts usually exploit large-scale entity-related text corpora or knowledge graph (KG) embeddings as auxiliary information to facilitate answer selection. However, the rich semantics implied in off-the-shelf relation paths between entities is far from well explored. This paper proposes improving multi-hop KGQA by exploiting relation paths' hybrid semantics. Specifically, we integrate explicit textual information and implicit KG structural features of relation paths based on a novel rotate-and-scale entity link prediction framework. Extensive experiments on three existing KGQA datasets demonstrate the superiority of our method, especially in multi-hop scenarios. Further investigation confirms our method's systematical coordination between questions and relation paths to identify answer entities.