Leveraging Table Content for Zero-shot Text-to-SQL  with Meta-Learning

Chen, Yongrui; Guo, Xinnan; Wang, Chaojie; Qiu, Jian; Qi, Guilin; Wang, Meng; Li, Huiying

doi:10.1609/aaai.v35i5.16519

Cited by 4 publications

(2 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The text-to-SQL dataset ESQL [43] in the electricity domain is sourced from real power energy agencies. Its tabular data cover multiple dimensions such as time, region, power suppliers, user scale, project progress, enterprise profitability, and more.…”

Section: Data Characteristics In Specific Domainsmentioning

confidence: 99%

Domain-Specific Few-Shot Table Prompt Question Answering via Contrastive Exemplar Selection

Mo,

Xiao,

Zhang

et al. 2024

Algorithms

View full text Add to dashboard Cite

As a crucial task in natural language processing, table question answering has garnered significant attention from both the academic and industrial communities. It enables intelligent querying and question answering over structured data by translating natural language into corresponding SQL statements. Recently, there have been notable advancements in the general domain table question answering task, achieved through prompt learning with large language models. However, in specific domains, where tables often have a higher number of columns and questions tend to be more complex, large language models are prone to generating invalid SQL or NoSQL statements. To address the above issue, this paper proposes a novel few-shot table prompt question answering approach. Specifically, we design a prompt template construction strategy for structured SQL generation. It utilizes prompt templates to restructure the input for each test data and standardizes the model output, which can enhance the integrity and validity of generated SQL. Furthermore, this paper introduces a contrastive exemplar selection approach based on the question patterns and formats in domain-specific contexts. This enables the model to quickly retrieve the relevant exemplars and learn characteristics about given question. Experimental results on the two datasets in the domains of electric energy and structural inspection show that the proposed approach outperforms the baseline models across all comparison settings.

show abstract

Section: Data Characteristics In Specific Domainsmentioning

confidence: 99%

Domain-Specific Few-Shot Table Prompt Question Answering via Contrastive Exemplar Selection

Mo,

Xiao,

Zhang

et al. 2024

Algorithms

View full text Add to dashboard Cite

show abstract

“…Text-to-SQL Research on text-to-SQL can be roughly divided into three directions. The first one is the single-table task (Zhong, Xiong, and Socher 2017;Hwang et al 2019;Chen et al 2021a;Xu et al 2022), whose target SQL programs contain only simple syntaxes. The second direction is a cross-domain multi-table scenario (Yu et al 2018).…”

Section: Related Workmentioning

confidence: 99%

Learn from Yesterday: A Semi-supervised Continual Learning Method for Supervision-Limited Text-to-SQL Task Streams

Chen¹,

Guo²,

et al. 2023

AAAI

View full text Add to dashboard Cite

Conventional text-to-SQL studies are limited to a single task with a fixed-size training and test set. When confronted with a stream of tasks common in real-world applications, existing methods struggle with the problems of insufficient supervised data and high retraining costs. The former tends to cause overfitting on unseen databases for the new task, while the latter makes a full review of instances from past tasks impractical for the model, resulting in forgetting of learned SQL structures and database schemas. To address the problems, this paper proposes integrating semi-supervised learning (SSL) and continual learning (CL) in a stream of text-to-SQL tasks and offers two promising solutions in turn. The first solution Vanilla is to perform self-training, augmenting the supervised training data with predicted pseudo-labeled instances of the current task, while replacing the full volume retraining with episodic memory replay to balance the training efficiency with the performance of previous tasks. The improved solution SFNet takes advantage of the intrinsic connection between CL and SSL. It uses in-memory past information to help current SSL, while adding high-quality pseudo instances in memory to improve future replay. The experiments on two datasets shows that SFNet outperforms the widely-used SSL-only and CL-only baselines on multiple metrics.

show abstract

HFD: Hierarchical feature decoupling for SQL generation from text

Zhang,

Hu,

Liu

et al. 2024

IDA

View full text Add to dashboard Cite

Text-to-SQL, a computational linguistics task, seeks to facilitate the conversion of natural language queries into SQL queries. Recent methodologies have leveraged the concept of slot-filling in conjunction with predetermined SQL templates to effectively bridge the semantic gap between natural language questions and structured database queries, achieving commendable performance by harnessing the power of multi-task learning. However, employing identical features across diverse tasks is an ill-suited practice, fraught with inherent drawbacks. Firstly, based on our observation, there are clear boundaries in the natural language corresponding to SELECT and WHERE clauses. Secondly, the exclusive features integral to each subtask are inadequately emphasized and underutilized, thereby hampering the acquisition of discriminative features for each specific subtask. In an endeavor to rectify these issues, the present work introduces an innovative approach: the hierarchical feature decoupling model for SQL query generation from natural language. This novel approach involves the deliberate separation of features pertaining to subtasks within both SELECT and WHERE clauses, further dissociating these features at the subtask level to foster better model performance. Empirical results derived from experiments conducted on the WikiSQL benchmark dataset reveal the superiority of the proposed approach over several state-of-the-art baseline methods in the context of text-to-SQL query generation.

show abstract

Leveraging Table Content for Zero-shot Text-to-SQL with Meta-Learning

Cited by 4 publications

References 11 publications

Domain-Specific Few-Shot Table Prompt Question Answering via Contrastive Exemplar Selection

Domain-Specific Few-Shot Table Prompt Question Answering via Contrastive Exemplar Selection

Learn from Yesterday: A Semi-supervised Continual Learning Method for Supervision-Limited Text-to-SQL Task Streams

HFD: Hierarchical feature decoupling for SQL generation from text

Contact Info

Product

Resources

About