Modeling Global Semantics for Question Answering over Knowledge Bases
This work aims to improve the accuracy of question answering over knowledge bases for users by better understanding the underlying structure of natural language questions, representing an incremental improvement in semantic parsing.
This paper addresses the challenge of question answering over knowledge bases (KBQA) by focusing on the internal structure of questions rather than just relation matching. The authors propose gRGCN, a relational graph convolutional network (RGCN)-based model, which extracts global semantics from questions and query graphs, including structural and relational semantics, and achieves superior performance on benchmark datasets.
Semantic parsing, as an important approach to question answering over knowledge bases (KBQA), transforms a question into the complete query graph for further generating the correct logical query. Existing semantic parsing approaches mainly focus on relations matching with paying less attention to the underlying internal structure of questions (e.g., the dependencies and relations between all entities in a question) to select the query graph. In this paper, we present a relational graph convolutional network (RGCN)-based model gRGCN for semantic parsing in KBQA. gRGCN extracts the global semantics of questions and their corresponding query graphs, including structure semantics via RGCN and relational semantics (label representation of relations between entities) via a hierarchical relation attention mechanism. Experiments evaluated on benchmarks show that our model outperforms off-the-shelf models.