# Weakly Supervised Text-to-SQL Parsing through Question Decomposition arXiv: https://arxiv.org/abs/2112.06311 ยท HTML: https://mlsanity.com/paper/2112.06311/ ## Key facts - Cited by 15 papers in the map (data through 14 Oct 2026). - Builds on 24 of its 59 references that are in the map. - First posted on arXiv 12 Dec 2021. ## Builds on (most cited first, 24 of 24) - [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014) - [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019) - [Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task](https://mlsanity.com/paper/1809.08887/) (2018) - [Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning](https://mlsanity.com/paper/1709.00103/) (2017) - [Compositional Semantic Parsing on Semi-Structured Tables](https://mlsanity.com/paper/1508.00305/) (2015) - [RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parsers](https://mlsanity.com/paper/1911.04942/) (2019) - [PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models](https://mlsanity.com/paper/2109.05093/) (2021) - [Snorkel: Rapid Training Data Creation with Weak Supervision](https://mlsanity.com/paper/1711.10160/) (2017) - [Towards Complex Text-to-SQL in Cross-Domain Database with Intermediate Representation](https://mlsanity.com/paper/1905.08205/) (2019) - [GraPPa: Grammar-Augmented Pre-Training for Table Semantic Parsing](https://mlsanity.com/paper/2009.13845/) (2020) - [Compositional Generalization and Natural Language Variation: Can a Semantic Parsing Approach Handle Both?](https://mlsanity.com/paper/2010.12725/) (2020) - [Improving Text-to-SQL Evaluation Methodology](https://mlsanity.com/paper/1806.09029/) (2018) - [Bridging Textual and Tabular Data for Cross-Domain Text-to-SQL Semantic Parsing](https://mlsanity.com/paper/2012.12627/) (2020) - [Break It Down: A Question Understanding Benchmark](https://mlsanity.com/paper/2001.11770/) (2020) - [Structure-Grounded Pretraining for Text-to-SQL](https://mlsanity.com/paper/2010.12773/) (2020) - [Coarse-to-Fine Decoding for Neural Semantic Parsing](https://mlsanity.com/paper/1805.04793/) (2018) - [KaggleDBQA: Realistic Evaluation of Text-to-SQL Parsers](https://mlsanity.com/paper/2106.11455/) (2021) - [SmBoP: Semi-autoregressive Bottom-up Semantic Parsing](https://mlsanity.com/paper/2010.12412/) (2020) - [Unlocking Compositional Generalization in Pre-trained Models Using Intermediate Representations](https://mlsanity.com/paper/2104.07478/) (2021) - [A Comparative Survey of Recent Natural Language Interfaces for Databases](https://mlsanity.com/paper/1906.08990/) (2019) - [Learning Semantic Parsers from Denotations with Latent Structured Alignments and Abstract Programs](https://mlsanity.com/paper/1909.04165/) (2019) - [Obtaining Faithful Interpretations from Compositional Neural Networks](https://mlsanity.com/paper/2005.00724/) (2020) - [Break, Perturb, Build: Automatic Perturbation of Reasoning Paths Through Question Decomposition](https://mlsanity.com/paper/2107.13935/) (2021) - [SPARQLing Database Queries from Intermediate Question Decompositions](https://mlsanity.com/paper/2109.06162/) (2021) ## Built on by (most cited first, 15 of 15) - [Exploring Chain-of-Thought Style Prompting for Text-to-SQL](https://mlsanity.com/paper/2305.14215/) (2023) - [RSL-SQL: Robust Schema Linking in Text-to-SQL Generation](https://mlsanity.com/paper/2411.00073/) (2024) - [MAG-SQL: Multi-Agent Generative Approach with Soft Schema Linking and Iterative Sub-SQL Refinement for Text-to-SQL](https://mlsanity.com/paper/2408.07930/) (2024) - [Disambiguate First, Parse Later: Generating Interpretations for Ambiguity Resolution in Semantic Parsing](https://mlsanity.com/paper/2502.18448/) (2025) - [Towards Understanding the Generalization of Medical Text-to-SQL Models and Datasets](https://mlsanity.com/paper/2303.12898/) (2023) - [Superlatives in Context: Modeling the Implicit Semantics of Superlatives](https://mlsanity.com/paper/2405.20967/) (2024) - [A Neural Divide-and-Conquer Reasoning Framework for Image Retrieval from Linguistically Complex Text](https://mlsanity.com/paper/2305.02265/) (2023) - [Generating Tables from the Parametric Knowledge of Language Models](https://mlsanity.com/paper/2406.10922/) (2024) - [Warmup Generations: A Task-Agnostic Approach for Guiding Sequence-to-Sequence Learning with Unsupervised Initial State Generation](https://mlsanity.com/paper/2502.12304/) (2025) - [Semantic Parsing for Complex Data Retrieval: Targeting Query Plans vs. SQL for No-Code Access to Relational Databases](https://mlsanity.com/paper/2312.14798/) (2023) - [Semantic Parsing with Candidate Expressions for Knowledge Base Question Answering](https://mlsanity.com/paper/2410.00414/) (2024) - [Beyond Natural Language Plans: Structure-Aware Planning for Query-Focused Table Summarization](https://mlsanity.com/paper/2507.22829/) (2025) - [Decomposed Prompting Does Not Fix Knowledge Gaps, But Helps Models Say "I Don't Know"](https://mlsanity.com/paper/2602.04853/) (2026) - [Searching for Better Database Queries in the Outputs of Semantic Parsers](https://mlsanity.com/paper/2210.07201/) (2022) - [CAPER: Clause-Aligned Process Supervision for Text-to-SQL](https://mlsanity.com/paper/2606.03327/) (2026) ## Abstract (arXiv) Text-to-SQL parsers are crucial in enabling non-experts to effortlessly query relational data. Training such parsers, by contrast, generally requires expertise in annotating natural language (NL) utterances with corresponding SQL queries. In this work, we propose a weak supervision approach for training text-to-SQL parsers. We take advantage of the recently proposed question meaning representation called QDMR, an intermediate between NL and formal query languages. Given questions, their QDMR structures (annotated by non-experts or automatically predicted), and the answers, we are able to automatically synthesize SQL queries that are used to train text-to-SQL models. We test our approach by experimenting on five benchmark datasets. Our results show that the weakly supervised models perform competitively with those trained on annotated NL-SQL data. Overall, we effectively train text-to-SQL parsers, while using zero SQL annotations.