Enhancing Complex Question Answering over Knowledge Graphs through Evidence Pattern Retrieval
This addresses the challenge of complex question answering for users of knowledge graphs, representing an incremental advance in subgraph extraction methods.
The paper tackled the problem of subgraph extraction in knowledge graph question answering by proposing Evidence Pattern Retrieval (EPR) to model structural dependencies, resulting in over 10-point F1 score improvements on ComplexWebQuestions and competitive performance on WebQuestionsSP.
Information retrieval (IR) methods for KGQA consist of two stages: subgraph extraction and answer reasoning. We argue current subgraph extraction methods underestimate the importance of structural dependencies among evidence facts. We propose Evidence Pattern Retrieval (EPR) to explicitly model the structural dependencies during subgraph extraction. We implement EPR by indexing the atomic adjacency pattern of resource pairs. Given a question, we perform dense retrieval to obtain atomic patterns formed by resource pairs. We then enumerate their combinations to construct candidate evidence patterns. These evidence patterns are scored using a neural model, and the best one is selected to extract a subgraph for downstream answer reasoning. Experimental results demonstrate that the EPR-based approach has significantly improved the F1 scores of IR-KGQA methods by over 10 points on ComplexWebQuestions and achieves competitive performance on WebQuestionsSP.