SPARQA: Skeleton-based Semantic Parsing for Complex Questions over Knowledge Bases
This addresses the challenge of handling complex questions in knowledge base querying, though it appears incremental as it builds on existing semantic parsing methods.
The paper tackles the problem of low accuracy in semantic parsing for long complex questions over knowledge bases by introducing a novel skeleton grammar and BERT-based parsing algorithm, resulting in improved accuracy for downstream parsing.
Semantic parsing transforms a natural language question into a formal query over a knowledge base. Many existing methods rely on syntactic parsing like dependencies. However, the accuracy of producing such expressive formalisms is not satisfying on long complex questions. In this paper, we propose a novel skeleton grammar to represent the high-level structure of a complex question. This dedicated coarse-grained formalism with a BERT-based parsing algorithm helps to improve the accuracy of the downstream fine-grained semantic parsing. Besides, to align the structure of a question with the structure of a knowledge base, our multi-strategy method combines sentence-level and word-level semantics. Our approach shows promising performance on several datasets.