Results 1 to 10 of about 2,491,472 (222)

DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction [PDF]

Neural Information Processing Systems, 2023
We study the problem of decomposing a complex text-to-sql task into smaller sub-tasks and how such a decomposition can significantly improve the performance of Large Language Models (LLMs) in the reasoning process.
Mohammadreza Pourreza, Davood Rafiei
core   +5 more sources

FinSQL: Model-Agnostic LLMs-based Text-to-SQL Framework for Financial Analysis [PDF]

arXiv
Text-to-SQL, which provides zero-code interface for operating relational databases, has gained much attention in financial analysis; because, financial professionals may not well-skilled in SQL programming. However, until now, there is no practical Text-to-SQL benchmark dataset for financial analysis, and existing Text-to-SQL methods have not ...
Chen, Lu, Fan, Yijiang, Gao, Yunjun, Lin, Jinshu, Lou, Dongfang, Mao, Yuren, Mi, Yu, Zhang, Chao   +7 more
arxiv   +4 more sources

Exploring Chain-of-Thought Style Prompting for Text-to-SQL [PDF]

Conference on Empirical Methods in Natural Language Processing, 2023
In-context learning with large language models (LLMs) has recently caught increasing attention due to its superior few-shot performance on various tasks. However, its performance on text-to-SQL parsing still has much room for improvement.
Chang-You Tai, Ziru Chen, Tianshu Zhang, Xiang Deng, Huan Sun   +4 more
core   +5 more sources

Improving Text-to-SQL with a Hybrid Decoding Method [PDF]

Entropy, 2023
Text-to-SQL is a task that converts natural language questions into SQL queries. Recent text-to-SQL models employ two decoding methods: sketch-based and generation-based, but each has its own shortcomings.
Geunyeong Jeong, Mirae Han, Seulgi Kim, Yejin Lee, Joosang Lee, Seongsik Park, Harksoo Kim   +6 more
doaj   +2 more sources

DIR: A Large-Scale Dialogue Rewrite Dataset for Cross-Domain Conversational Text-to-SQL [PDF]

Applied Sciences, 2023
Semantic co-reference and ellipsis always lead to information deficiency when parsing natural language utterances with SQL in a multi-turn dialogue (i.e., conversational text-to-SQL task).
Jieyu Li, Zhi Chen, Lu Chen, Zichen Zhu, Hanqi Li, Ruisheng Cao, Kai Yu   +6 more
doaj   +2 more sources

CQR-SQL: Conversational Question Reformulation Enhanced Context-Dependent Text-to-SQL Parsers [PDF]

arXiv, 2022
Context-dependent text-to-SQL is the task of translating multi-turn questions into database-related SQL queries. Existing methods typically focus on making full use of history context or previously predicted SQL for currently SQL parsing, while neglecting to explicitly comprehend the schema and conversational dependency, such as co-reference, ellipsis ...
Dongling Xiao, Linzheng Chai, Qianwen Zhang, Yan Zhao, Zhoujun Li, Yunbo Cao   +5 more
arxiv   +3 more sources

Natural SQL: Making SQL Easier to Infer from Natural Language Specifications [PDF]

arXiv, 2021
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)
Chen, X, Drake, J, Gan, Y, Purver, M, Woodward, JR, Xie, J, Zhang, Q   +6 more
arxiv   +4 more sources

Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation [PDF]

Proceedings of the VLDB Endowment, 2023
Large language models (LLMs) have emerged as a new paradigm for Text-to-SQL task. However, the absence of a systematical benchmark inhibits the development of designing effective, efficient and economic LLM-based Text-to-SQL solutions.
Ding, Bolin, Gao, Dawei, Li, Yaliang, Qian, Yichen, Sun, Xiuyu, Wang, Haibin, Zhou, Jingren   +6 more
core   +2 more sources

C3: Zero-shot Text-to-SQL with ChatGPT [PDF]

arXiv.org, 2023
This paper proposes a ChatGPT-based zero-shot Text-to-SQL method, dubbed C3, which achieves 82.3\% in terms of execution accuracy on the holdout test set of Spider and becomes the state-of-the-art zero-shot Text-to-SQL method on the Spider Challenge.
Chen, lu, Dong, Xuemei, Gao, Yunjun, Ge, Yuhang, Lin, Jinshu, Lou, Dongfang, Mao, Yuren, Zhang, Chao   +7 more
core   +2 more sources

MedT5SQL: a transformers-based large language model for text-to-SQL conversion in the healthcare domain [PDF]

Frontiers in Big Data
IntroductionIn response to the increasing prevalence of electronic medical records (EMRs) stored in databases, healthcare staff are encountering difficulties retrieving these records due to their limited technical expertise in database operations.
Alaa Marshan, Anwar Nais Almutairi, Athina Ioannou, David Bell, Asmat Monaghan, Mahir Arzoky   +5 more
doaj   +2 more sources