Home > Research > Publications & Outputs > Enhancing Text-to-SQL Translation for Financial...

Electronic data

  • 2312.14725v1

    Accepted author manuscript, 917 KB, PDF document

    Available under license: CC BY: Creative Commons Attribution 4.0 International License

Links

Text available via DOI:

Keywords

View graph of relations

Enhancing Text-to-SQL Translation for Financial System Design

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Published

Standard

Enhancing Text-to-SQL Translation for Financial System Design. / Song, Yewei; Ezzini, Saad; Tang, Xunzhu et al.
Proceedings - 2024 ACM/IEEE 44th International Conference on Software Engineering: New Ideas and Emerging Results, ICSE-SEIP 2024. New York: ACM, 2024. p. 252-262.

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Harvard

Song, Y, Ezzini, S, Tang, X, Lothritz, C, Klein, J, Bissyandé, T, Boytsov, A, Ble, U & Goujon, A 2024, Enhancing Text-to-SQL Translation for Financial System Design. in Proceedings - 2024 ACM/IEEE 44th International Conference on Software Engineering: New Ideas and Emerging Results, ICSE-SEIP 2024. ACM, New York, pp. 252-262, 2024 ACM/IEEE 44th International Conference on Software Engineering: New Ideas and Emerging Results, ICSE-SEIP 2024, Lisbon, Portugal, 14/04/24. https://doi.org/10.1145/3639477.3639732

APA

Song, Y., Ezzini, S., Tang, X., Lothritz, C., Klein, J., Bissyandé, T., Boytsov, A., Ble, U., & Goujon, A. (2024). Enhancing Text-to-SQL Translation for Financial System Design. In Proceedings - 2024 ACM/IEEE 44th International Conference on Software Engineering: New Ideas and Emerging Results, ICSE-SEIP 2024 (pp. 252-262). ACM. https://doi.org/10.1145/3639477.3639732

Vancouver

Song Y, Ezzini S, Tang X, Lothritz C, Klein J, Bissyandé T et al. Enhancing Text-to-SQL Translation for Financial System Design. In Proceedings - 2024 ACM/IEEE 44th International Conference on Software Engineering: New Ideas and Emerging Results, ICSE-SEIP 2024. New York: ACM. 2024. p. 252-262 doi: 10.1145/3639477.3639732

Author

Song, Yewei ; Ezzini, Saad ; Tang, Xunzhu et al. / Enhancing Text-to-SQL Translation for Financial System Design. Proceedings - 2024 ACM/IEEE 44th International Conference on Software Engineering: New Ideas and Emerging Results, ICSE-SEIP 2024. New York : ACM, 2024. pp. 252-262

Bibtex

@inproceedings{09a01ba052734c6b8735de966e96cfb2,
title = "Enhancing Text-to-SQL Translation for Financial System Design",
abstract = "Text-to-SQL, the task of translating natural language questions into SQL queries, is part of various business processes. Its automation, which is an emerging challenge, will empower software practitioners to seamlessly interact with relational databases using natural language, thereby bridging the gap between business needs and software capabilities. In this paper, we consider Large Language Models (LLMs), which have achieved state of the art for various NLP tasks. Specifically, we benchmark Text-to-SQL performance, the evaluation methodologies, as well as input optimization (e.g., prompting). In light of the empirical observations that we have made, we propose two novel metrics that were designed to adequately measure the similarity between SQL queries. Overall, we share with the community various findings, notably on how to select the right LLM on Text-to-SQL tasks. We further demonstrate that a tree-based edit distance constitutes a reliable metric for assessing the similarity between generated SQL queries and the oracle for benchmarking Text2SQL approaches. This metric is important as it relieves researchers from the need to perform computationally expensive experiments such as executing generated queries as done in prior works. Our work implements financial domain use cases and, therefore contributes to the advancement of Text2SQL systems and their practical adoption in this domain.",
keywords = "cs.SE",
author = "Yewei Song and Saad Ezzini and Xunzhu Tang and Cedric Lothritz and Jacques Klein and Tegawend{\'e} Bissyand{\'e} and Andrey Boytsov and Ulrick Ble and Anne Goujon",
year = "2024",
month = apr,
day = "14",
doi = "10.1145/3639477.3639732",
language = "English",
pages = "252--262",
booktitle = "Proceedings - 2024 ACM/IEEE 44th International Conference on Software Engineering",
publisher = "ACM",
note = "2024 ACM/IEEE 44th International Conference on Software Engineering: New Ideas and Emerging Results, ICSE-SEIP 2024 ; Conference date: 14-04-2024 Through 20-04-2024",

}

RIS

TY - GEN

T1 - Enhancing Text-to-SQL Translation for Financial System Design

AU - Song, Yewei

AU - Ezzini, Saad

AU - Tang, Xunzhu

AU - Lothritz, Cedric

AU - Klein, Jacques

AU - Bissyandé, Tegawendé

AU - Boytsov, Andrey

AU - Ble, Ulrick

AU - Goujon, Anne

PY - 2024/4/14

Y1 - 2024/4/14

N2 - Text-to-SQL, the task of translating natural language questions into SQL queries, is part of various business processes. Its automation, which is an emerging challenge, will empower software practitioners to seamlessly interact with relational databases using natural language, thereby bridging the gap between business needs and software capabilities. In this paper, we consider Large Language Models (LLMs), which have achieved state of the art for various NLP tasks. Specifically, we benchmark Text-to-SQL performance, the evaluation methodologies, as well as input optimization (e.g., prompting). In light of the empirical observations that we have made, we propose two novel metrics that were designed to adequately measure the similarity between SQL queries. Overall, we share with the community various findings, notably on how to select the right LLM on Text-to-SQL tasks. We further demonstrate that a tree-based edit distance constitutes a reliable metric for assessing the similarity between generated SQL queries and the oracle for benchmarking Text2SQL approaches. This metric is important as it relieves researchers from the need to perform computationally expensive experiments such as executing generated queries as done in prior works. Our work implements financial domain use cases and, therefore contributes to the advancement of Text2SQL systems and their practical adoption in this domain.

AB - Text-to-SQL, the task of translating natural language questions into SQL queries, is part of various business processes. Its automation, which is an emerging challenge, will empower software practitioners to seamlessly interact with relational databases using natural language, thereby bridging the gap between business needs and software capabilities. In this paper, we consider Large Language Models (LLMs), which have achieved state of the art for various NLP tasks. Specifically, we benchmark Text-to-SQL performance, the evaluation methodologies, as well as input optimization (e.g., prompting). In light of the empirical observations that we have made, we propose two novel metrics that were designed to adequately measure the similarity between SQL queries. Overall, we share with the community various findings, notably on how to select the right LLM on Text-to-SQL tasks. We further demonstrate that a tree-based edit distance constitutes a reliable metric for assessing the similarity between generated SQL queries and the oracle for benchmarking Text2SQL approaches. This metric is important as it relieves researchers from the need to perform computationally expensive experiments such as executing generated queries as done in prior works. Our work implements financial domain use cases and, therefore contributes to the advancement of Text2SQL systems and their practical adoption in this domain.

KW - cs.SE

U2 - 10.1145/3639477.3639732

DO - 10.1145/3639477.3639732

M3 - Conference contribution/Paper

SP - 252

EP - 262

BT - Proceedings - 2024 ACM/IEEE 44th International Conference on Software Engineering

PB - ACM

CY - New York

T2 - 2024 ACM/IEEE 44th International Conference on Software Engineering: New Ideas and Emerging Results, ICSE-SEIP 2024

Y2 - 14 April 2024 through 20 April 2024

ER -