Semantic Decomposition of Question and SQL for Text-to-SQL Parsing
Submission Type: Regular Long Paper
Submission Track: Semantics: Lexical, Sentence level, Document Level, Textual Inference, etc.
Submission Track 2: Question Answering
Keywords: semantic parsing, text-to-sql, question decomposition, compositionality
TL;DR: To improve compositional learning of text-to-SQL, we introduce QPL, an executable modular semantic SQL transformation. With Spider adapted to QPL we learn a Question Decomposer aligned with QPL, leading to effective parsing of complex queries.
Abstract: Text-to-SQL semantic parsing faces challenges in generalizing to cross-domain and complex queries. Recent research has employed a question decomposition strategy to enhance the parsing of complex SQL queries.However, this strategy encounters two major obstacles: (1) existing datasets lack question decomposition;
(2) due to the syntactic complexity of SQL, most complex queries cannot be disentangled into sub-queries that can be readily recomposed.
To address these challenges, we propose a new modular Query Plan Language (QPL) that systematically decomposes SQL queries into simple and regular sub-queries. We develop a translator from SQL to QPL by leveraging analysis of SQL server query optimization plans, and we augment the Spider dataset with QPL programs.
Experimental results demonstrate that the modular nature of QPL benefits existing semantic-parsing architectures,
and training text-to-QPL parsers is more effective than text-to-SQL parsing for semantically equivalent queries.
The QPL approach offers two additional advantages: (1) QPL programs can be paraphrased as simple questions, which allows us to create a dataset of (complex question, decomposed questions). Training on this dataset, we obtain a Question Decomposer for data retrieval that is sensitive to database schemas.
(2) QPL is more accessible to non-experts for complex queries, leading to more interpretable output from the semantic parser.
Submission Number: 2104
Loading