Decoupling the Skeleton Parsing and Schema Linking for Text-to-SQL

Classés selon la proximité de leur titre et de leur résumé avec ceux de cet article. Sélectionnez-en pour les lire ensemble.

Les articles les plus proches

1. Très proche Cité par cet article Pas pertinent

   RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parsers

   Bailin Wang, Richard Shin, Xiaodong Liu et al. · 2019 · Annual Meeting of the Association for Computational Linguistics · cité 963 fois · Pas encore résumé

   Résumé scientifique

   When translating natural language questions into SQL queries to answer questions from a database, contemporary semantic parsing models struggle to generalize to unseen database schemas. The generalization challenge lies in (a) encoding the database relations in an accessible way for the semantic parser, and (b) modeling alignment between database columns and their mentions in a given query. We present a unified framework, based on the relation-aware self-attention mechanism, to address schema encoding, schema linking, and feature representation within a text-to-SQL encoder. On the challenging Spider dataset this framework boosts the exact match accuracy to 57.2%, surpassing its best counterp…

2. Très proche Cite cet article Pas pertinent

   LEAF-SQL: Level-Wise Exploration with Adaptive Fine-Graining for Text-to-SQL Skeleton Prediction

   Zhao Tan, Xi-Ping Liu, Qing Shu et al. · 2026 · IEEE International Conference on Data Engineering · cité 1 fois · Pas encore résumé

   Résumé scientifique

   Text-to-SQL translates natural language questions into executable SQL queries, enabling intuitive database access for non-experts. While large language models achieve strong performance on Text-to-SQL with prompting, they still struggle with complex queries that involve deeply nested logic or multiple clauses. A widely used approach employs SQL skeletons-intermediate representations of query logic-to streamline generation, but existing methods are limited by their reliance on a single structural hypothesis and lack of progressive reasoning. To overcome these limitations, we propose LEAF-SQL, a novel framework that reframes skeleton prediction as a coarse-to-fine tree search process. LEAF-SQL…

3. Très proche Pas pertinent

   Improving Text-to-SQL with Schema Dependency Learning

   Binyuan Hui, Xiang Shi, Ruiying Geng et al. · 2021 · arXiv.org · preprint, non relu par les pairs · cité 53 fois · Pas encore résumé

   Résumé scientifique

   Text-to-SQL aims to map natural language questions to SQL queries. The sketch-based method combined with execution-guided (EG) decoding strategy has shown a strong performance on the WikiSQL benchmark. However, execution-guided decoding relies on database execution, which significantly slows down the inference process and is hence unsatisfactory for many real-world applications. In this paper, we present the Schema Dependency guided multi-task Text-to-SQL model (SDSQL) to guide the network to effectively capture the interactions between questions and schemas. The proposed model outperforms all existing methods in both the settings with or without EG. We show the schema dependency learning pa…

4. Très proche Cite cet article Pas pertinent

   Lightweight Text-to-SQL Enhancement via Schema Ranking and Skeleton-Constrained CoT Distillation

   Wei-Hong Gao, Xinying Li, Bin Qin · 2025 · 2025 5th International Symposium on Artificial Intelligence and Big Data (AIBDF) · Pas encore résumé

   Résumé scientifique

   Cross-database Text-to-SQL tasks require models to perform both structural planning (Skeleton Parsing) and Schema Linking on unfamiliar database schemas. The high coupling of these two subtasks significantly increases generation complexity and error rates. To address this challenge, this paper proposes a two-stage framework based on Chain-of-Thought (CoT) enhancement and decoupled generation. The first stage utilizes Parameter-Efficient Fine-Tuning (PEFT) to output a Ranked Schema sequence and a SQL Skeleton, thereby reducing the search space and providing macroscopic structural guidance. The second stage employs explicit Chain-of-Thought reasoning under the dual constraints of the skeleton …

5. Très proche Cite cet article Pas pertinent

   RSL-SQL: Robust Schema Linking in Text-to-SQL Generation

   Zhenbiao Cao, Yuanlei Zheng, Zhihao Fan et al. · 2024 · arXiv.org · preprint, non relu par les pairs · cité 95 fois · Pas encore résumé

   Résumé scientifique

   Text-to-SQL generation aims to translate natural language questions into SQL statements. In Text-to-SQL based on large language models, schema linking is a widely adopted strategy to streamline the input for LLMs by selecting only relevant schema elements, therefore reducing noise and computational overhead. However, schema linking faces risks that require caution, including the potential omission of necessary elements and disruption of database structural integrity. To address these challenges, we propose a novel framework called RSL-SQL that combines bidirectional schema linking, contextual information augmentation, binary selection strategy, and multi-turn self-correction. We improve the …

6. Très proche Pas pertinent

   T5-SR: A Unified Seq-to-Seq Decoding Strategy for Semantic Parsing

   Yuntao Li, Zhenpeng Su, Yutian Li et al. · 2023 · IEEE International Conference on Acoustics, Speech, and Signal Processing · cité 6 fois · Pas encore résumé

   Résumé scientifique

   Translating natural language queries into SQLs in a seq2seq manner has attracted much attention recently. However, compared with abstract-syntactic-tree-based SQL generation, seq2seq semantic parsers face much more challenges, including poor quality on schematical information prediction and poor semantic coherence between natural language queries and SQLs. This paper analyses the above difficulties and proposes a seq2seq-oriented decoding strategy called SR, which includes a new intermediate representation SSQL and a reranking method with score re-estimator to solve the above obstacles respectively. Experimental results demonstrate the effectiveness of our proposed techniques and T5-SR-3b ac…

7. Très proche Cité par cet article Utilisé en profondeur par cet article Pas pertinent

   S^2SQL: Injecting Syntax to Question-Schema Interaction Graph Encoder for Text-to-SQL Parsers

   Binyuan Hui, Ruiying Geng, Lihan Wang et al. · 2022 · Findings · cité 80 fois · Pas encore résumé

   Résumé scientifique

   The task of converting a natural language question into an executable SQL query, known as text-to-SQL, is an important branch of semantic parsing. The state-of-the-art graph-based encoder has been successfully used in this task but does not model the question syntax well. In this paper, we propose S^2SQL, injecting Syntax to question-Schema graph encoder for Text-to-SQL parsers, which effectively leverages the syntactic dependency information of questions in text-to-SQL to improve the performance. We also employ the decoupling constraint to induce diverse relational edge embedding, which further improves the network’s performance. Experiments on the Spider and robustness setting Spider-Syn d…

8. Très proche Pas pertinent

   Grammar-based Neural Text-to-SQL Generation

   Kevin Lin, Ben Bogin, Mark Neumann et al. · 2019 · arXiv.org · preprint, non relu par les pairs · cité 65 fois · Pas encore résumé

   Résumé scientifique

   The sequence-to-sequence paradigm employed by neural text-to-SQL models typically performs token-level decoding and does not consider generating SQL hierarchically from a grammar. Grammar-based decoding has shown significant improvements for other semantic parsing tasks, but SQL and other general programming languages have complexities not present in logical formalisms that make writing hierarchical grammars difficult. We introduce techniques to handle these complexities, showing how to construct a schema-dependent grammar with minimal over-generation. We analyze these techniques on ATIS and Spider, two challenging text-to-SQL datasets, demonstrating that they yield 14--18\% relative reducti…

Les travaux antérieurs sur lesquels il s’appuie

1. Proche Utilisé en profondeur par cet article Pas pertinent

   RASAT: Integrating Relational Structures into Pretrained Seq2Seq Model for Text-to-SQL

   Jiexing Qi, Jingyao Tang, Ziwei He et al. · 2022 · Conference on Empirical Methods in Natural Language Processing · cité 176 fois · Pas encore résumé

   Résumé scientifique

   Relational structures such as schema linking and schema encoding have been validated as a key component to qualitatively translating natural language into SQL queries. However, introducing these structural relations comes with prices: they often result in a specialized model structure, which largely prohibits using large pretrained models in text-to-SQL. To address this problem, we propose RASAT: a Transformer seq2seq architecture augmented with relation-aware self-attention that could leverage a variety of relational structures while inheriting the pretrained parameters from the T5 model effectively. Our model can incorporate almost all types of existing relations in the literature, and in …

2. Proche Utilisé en profondeur par cet article Une méthode qu’il utilise Pas pertinent

   Natural SQL: Making SQL Easier to Infer from Natural Language Specifications

   Yujian Gan, Xin-Yun Chen, Jinxia Xie et al. · 2021 · Conference on Empirical Methods in Natural Language Processing · cité 162 fois · Pas encore résumé

   Résumé scientifique

   Addressing the mismatch between natural language descriptions and the corresponding SQL queries is a key challenge for text-to-SQL translation. To bridge this gap, we propose an SQL intermediate representation (IR) called Natural SQL (NatSQL). Specifically, NatSQL preserves the core functionalities of SQL, while it simplifies the queries as follows: (1) dispensing with operators and keywords such as GROUP BY, HAVING, FROM, JOIN ON, which are usually hard to find counterparts for in the text descriptions; (2) removing the need for nested subqueries and set operators; and (3) making schema linking easier by reducing the required number of schema items. On Spider, a challenging text-to-SQL benc…

3. Proche Utilisé en profondeur par cet article Une méthode qu’il utilise Pas pertinent

   SyntaxSQLNet: Syntax Tree Networks for Complex and Cross-Domain Text-to-SQL Task

   Tao Yu, Michihiro Yasunaga, Kai-Chou Yang et al. · 2018 · Conference on Empirical Methods in Natural Language Processing · cité 240 fois · Pas encore résumé

   Résumé scientifique

   Most existing studies in text-to-SQL tasks do not require generating complex SQL queries with multiple clauses or sub-queries, and generalizing to new, unseen databases. In this paper we propose SyntaxSQLNet, a syntax tree network to address the complex and cross-domain text-to-SQL generation task. SyntaxSQLNet employs a SQL specific syntax tree-based decoder with SQL generation path history and table-aware column attention encoders. We evaluate SyntaxSQLNet on a new large-scale text-to-SQL corpus containing databases with multiple tables and complex SQL queries containing multiple SQL clauses and nested queries. We use a database split setting where databases in the test set are unseen duri…

4. Proche Pas pertinent

   Towards Robustness of Text-to-SQL Models against Synonym Substitution

   Yujian Gan, Xin-Yun Chen, Qiuping Huang et al. · 2021 · Annual Meeting of the Association for Computational Linguistics · cité 196 fois · Pas encore résumé

   Résumé scientifique

   Recently, there has been significant progress in studying neural networks to translate text descriptions into SQL queries. Despite achieving good performance on some public benchmarks, existing text-to-SQL models typically rely on the lexical matching between words in natural language (NL) questions and tokens in table schemas, which may render the models vulnerable to attacks that break the schema linking mechanism. In this work, we investigate the robustness of text-to-SQL models to synonym substitution. In particular, we introduce Spider-Syn, a human-curated dataset based on the Spider benchmark for text-to-SQL translation. NL questions in Spider-Syn are modified from Spider, by replacing…

5. Proche Pas pertinent

   Robust Text-to-SQL Generation with Execution-Guided Decoding

   Chenglong Wang, Kedar Tatwawadi, M. Brockschmidt et al. · 2018 · arXiv: Computation and Language · preprint, non relu par les pairs · cité 136 fois · Pas encore résumé

   Résumé scientifique

   We consider the problem of neural semantic parsing, which translates natural language questions into executable SQL queries. We introduce a new mechanism, execution guidance, to leverage the semantics of SQL. It detects and excludes faulty programs during the decoding procedure by conditioning on the execution of partially generated program. The mechanism can be used with any autoregressive generative model, which we demonstrate on four state-of-the-art recurrent or template-based semantic parsing models. We demonstrate that execution guidance universally improves model performance on various text-to-SQL datasets with different scales and query complexity: WikiSQL, ATIS, and GeoQuery. As a r…

Les articles qui le citent

1. Proche Utilise cet article en profondeur Pas pertinent

   Scaling Text2SQL via LLM-efficient Schema Filtering with Functional Dependency Graph Rerankers

   Thanh Dat Hoang, T. Nguyen, T. T. Huynh et al. · 2025 · arXiv.org · preprint, non relu par les pairs · cité 3 fois · Pas encore résumé

   Résumé scientifique

   Most modern Text2SQL systems prompt large language models (LLMs) with entire schemas -- mostly column information -- alongside the user's question. While effective on small databases, this approach fails on real-world schemas that exceed LLM context limits, even for commercial models. The recent Spider 2.0 benchmark exemplifies this with hundreds of tables and tens of thousands of columns, where existing systems often break. Current mitigations either rely on costly multi-step prompting pipelines or filter columns by ranking them against user's question independently, ignoring inter-column structure. To scale existing systems, we introduce \toolname, an open-source, LLM-efficient schema filt…

2. Proche Utilise cet article en profondeur Pas pertinent

   LINC-SQL: A Collaborative Framework for Robust Text-to-SQL Generation

   Wei Wang, Dong-Dong Huo, Qin-Fu Yang et al. · 2026 · International Conference on Computer Supported Cooperative Work in Design · Pas encore résumé

   Résumé scientifique

   Text-to-SQL has advanced remarkably with Large Language Models (LLMs), yet existing paradigms still grapple with error-prone "blind retry" corrections and the difficulty of capturing complex semantic logic (e.g., JOIN paths). To address these gaps, we propose LINC-SQL, a collaborative two-stage framework. Stage 1 introduces a structured "Semantic Skeleton" as a logical blueprint, offering stricter constraints than traditional syntactic planning. Stage 2 executes iterative generation using a novel Classification-Based Execution Feedback (CB-EF) loop. By parsing errors to provide targeted repair instructions, CB-EF effectively avoids blind retries and the need for heavy critic models. Extensiv…

3. Proche Utilise cet article en profondeur Pas pertinent

   X-SQL: Expert Schema Linking and Understanding of Text-to-SQL with Multi-LLMs

   Da Peng · 2025 · arXiv.org · preprint, non relu par les pairs · cité 1 fois · Pas encore résumé

   Résumé scientifique

   With Large Language Models'(LLMs) emergent abilities on code generation tasks, Text-to-SQL has become one of the most popular downstream applications. Despite the strong results of multiple recent LLM-based Text-to-SQL frameworks, the research community often overlooks the importance of database schema information for generating high-quality SQL queries. We find that such schema information plays a significant or even dominant role in the Text-to-SQL task. To tackle this challenge, we propose a novel database schema expert with two components. We first introduce X-Linking, an LLM Supervised Finetuning (SFT)-based method that achieves superior Schema Linking results compared to existing open-…

4. Proche Utilise cet article en profondeur Pas pertinent

   CCS-SQL: Enhancing Text-to-SQL Framework for Computational Queries via Large Language Models

   Qi Ma, Shu-Ming Jiang, Zhi-Qiang Wei et al. · 2025 · IEEE International Joint Conference on Neural Network · Pas encore résumé

   Résumé scientifique

   The Text-to-SQL task is to convert natural language queries into Structured Query Language (SQL) to achieve a natural language interface for database queries. The current research on Text-to-SQL primarily focuses on handling complex queries (such as nested queries and multi-table joins), while neglecting those that require complex computations. To address this issue, this paper constructs a Text-to-SQL dataset with a relatively high proportion of computational questions, termed as ESDS, and designs a Text-to-SQL framework based on large language models, named CCS-SQL, to enhance the parsing capability for computational questions. The three core modules of the framework are Schema Linking(SL)…

5. Proche Utilise cet article en profondeur Pas pertinent

   Automated Validating and Fixing of Text-to-SQL Translation with Execution Consistency

   Yicun Yang, Zhao-Guo Wang, Yu-Bin Xia et al. · 2025 · Proc. ACM Manag. Data · cité 24 fois · Pas encore résumé

   Résumé scientifique

   State-of-the-art Text-to-SQL models rely on fine-tuning or few-shot prompting to help LLMs learn from training datasets containing mappings from natural language (NL) queries to SQL statements. Consequently, the quality of the dataset can greatly affect the accuracy of these Text-to-SQL models. Unlike other NL tasks, Text-to-SQL datasets are prone to errors despite extensive manual efforts due to the subtle semantics of SQL. Our study has found a non-negligible (>30%) portion of incorrect NL to SQL mapping cases exists in popular datasets Spider and BIRD. This paper aims to improve the quality of Text-to-SQL training datasets and thereby increase the accuracy of the resulting models. To do s…