Towards Knowledge-Intensive Text-to-SQL Semantic Parsing with Formulaic Knowledge
In this paper, we study the problem of knowledge-intensive text-to-SQL, in which domain knowledge is necessary to parse expert questions into SQL queries over domain-specific tables. We formalize this scenario by building a new Chinese benchmark KnowSQL consisting of domain-specific questions covering various domains. We then address this problem by presenting formulaic knowledge, rather than by annotating additional data examples. More concretely, we construct a formulaic knowledge bank as a domain knowledge base and propose a framework (ReGrouP) to leverage this formulaic knowledge during parsing. Experiments using ReGrouP demonstrate a significant 28.2% improvement overall on KnowSQL.
Code (1)
Tasks
Semantic ParsingText to SQLText-To-SQLMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
An Instance Level Approach for Shallow Semantic Parsing in Scientific Procedural Text
In specific domains, such as procedural scientific text, human labeled data for shallow semantic parsing is especially limited and expensive to create. Fortunately, such specific domains often use rather formulaic writin…
Relation PredictionSemantic ParsingSentenceComparing Knowledge-Intensive and Data-Intensive Models for English Resource Semantic Parsing
Abstract In this work, we present a phenomenon-oriented comparative analysis of the two dominant approaches in English Resource Semantic (ERS) parsing: classic, knowledge-intensive and neural, data-intensive models. To r…
Semantic ParsingA Comparative Analysis of Knowledge-Intensive and Data-Intensive Semantic Parsers
We present a phenomenon-oriented comparative analysis of the two dominant approaches in task-independent semantic parsing: classic, knowledge-intensive and neural, data-intensive models. To reflect state-of-the-art neura…
Semantic ParsingA methodology for the extraction of information about the usage of formulaic expressions in scientific texts
In this paper, we present a methodology for the extraction of formulaic expressions, which goes beyond the mere extraction of candidate patterns. Using a pipeline we are able to extract information about the usage of for…
UniRec-0.1B: Unified Text and Formula Recognition with 0.1B Parameters
Text and formulas constitute the core informational components of many documents. Accurately and efficiently recognizing both is crucial for developing robust and generalizable document parsing systems. Recently, vision-…