From Examples to Patterns: LLM-Generated Reg-ular Expressions
for Entity Extraction in Czech Clinical Texts

D 2024

From Examples to Patterns: LLM-Generated Reg-ular Expressions for Entity Extraction in Czech Clinical Texts

ZELINA, Petr

Základní údaje

Originální název

From Examples to Patterns: LLM-Generated Reg-ular Expressions for Entity Extraction in Czech Clinical Texts

Autoři

ZELINA, Petr

Vydání

Brno, Proceedings of the Eighteenth Workshop on Recent Advances in Slavonic Natural Languages Processing, RASLAN 2024, od s. 3-16, 14 s. 2024

Nakladatel

Tribun EU

Další údaje

Jazyk

angličtina

Typ výsledku

Stať ve sborníku

Obor

10200 1.2 Computer and information sciences

Stát vydavatele

Česká republika

Utajení

není předmětem státního či obchodního tajemství

Forma vydání

tištěná verze "print"

Odkazy

URL

Označené pro přenos do RIV

Ano

Kód RIV

RIV/00216224:14330/24:00138709

Organizační jednotka

Fakulta informatiky

ISBN

978-80-263-1835-4

ISSN

Klíčová slova anglicky

NLP; LLM; regex; text mining; clinical notes

Příznaky

Recenzováno

Změněno: 30. 1. 2025 15:53, RNDr. Petr Zelina

Anotace

V originále

Entity extraction in clinical texts is essential for converting unstructured data in clinical notes into structured formats, facilitating large-scale analysis and clinical decision support. Traditional methods often rely on handcrafted regular expressions (regexes), which, while effective, demand significant time and specialized knowledge to create -- resources that healthcare professionals may lack. We introduce a novel approach leveraging large language models (LLMs) to automate regex generation for clinical entity extraction. Our method involves prompting LLMs to generate regex patterns from examples, followed by iterative refinement using a feedback loop. Despite regex limitations, this approach is practical for extracting frequently patterned information common in clinical texts, such as dates, specific data about medical procedures or event detection. Our experiments on Czech clinical notes show this method outperforms current SOTA genetic-programming-based methods for generating regular expression patterns from examples, especially when there are few of them.

Návaznosti

MUNI/A/1590/2023, interní kód MU

Název: Využití technik umělé inteligence pro zpracování dat, komplexní analýzy a vizualizaci rozsáhlých dat

Investor: Masarykova univerzita, Využití technik umělé inteligence pro zpracování dat, komplexní analýzy a vizualizaci rozsáhlých dat

Citovat

ZELINA, Petr. From Examples to Patterns: LLM-Generated Reg-ular Expressions for Entity Extraction in Czech Clinical Texts. In Horák, Aleš and Rychlý, Pavel and Rambousek, Adam. Proceedings of the Eighteenth Workshop on Recent Advances in Slavonic Natural Languages Processing, RASLAN 2024. Brno: Tribun EU, 2024, s. 3-16. ISBN 978-80-263-1835-4.

@inproceedings{2472680,
   author = {Zelina, Petr},
   address = {Brno},
   booktitle = {Proceedings of the Eighteenth Workshop on Recent Advances in Slavonic Natural Languages Processing, RASLAN 2024},
   editor = {Horák, Aleš and Rychlý, Pavel and Rambousek, Adam},
   keywords = {NLP; LLM; regex; text mining; clinical notes},
   howpublished = {tištěná verze "print"},
   language = {eng},
   location = {Brno},
   isbn = {978-80-263-1835-4},
   pages = {3-16},
   publisher = {Tribun EU},
   title = {From Examples to Patterns: LLM-Generated Reg-ular Expressions for Entity Extraction in Czech Clinical Texts},
   url = {https://nlp.fi.muni.cz/raslan/2024/paper6.pdf},
   year = {2024}
}

TY  - CONF
ID  - 2472680
AU  - Zelina, Petr
PY  - 2024
TI  - From Examples to Patterns: LLM-Generated Reg-ular Expressions for Entity Extraction in Czech Clinical Texts
PB  - Tribun EU
CY  - Brno
SN  - 9788026318354
KW  - NLP
KW  - LLM
KW  - regex
KW  - text mining
KW  - clinical notes
UR  - https://nlp.fi.muni.cz/raslan/2024/paper6.pdf
N2  - Entity extraction in clinical texts is essential for converting unstructured data in clinical notes into structured formats, facilitating large-scale analysis and clinical decision support. Traditional methods often rely on handcrafted regular expressions (regexes), which, while effective, demand significant time and specialized knowledge to create -- resources that healthcare professionals may lack. We introduce a novel approach leveraging large language models (LLMs) to automate regex generation for clinical entity extraction. Our method involves prompting LLMs to generate regex patterns from examples, followed by iterative refinement using a feedback loop. Despite regex limitations, this approach is practical for extracting frequently patterned information common in clinical texts, such as dates, specific data about medical procedures or event detection. Our experiments on Czech clinical notes show this method outperforms current SOTA genetic-programming-based methods for generating regular expression patterns from examples, especially when there are few of them.
ER  -

ZELINA, Petr. From Examples to Patterns: LLM-Generated Reg-ular Expressions for Entity Extraction in Czech Clinical Texts. In Horák, Aleš and Rychlý, Pavel and Rambousek, Adam. \textit{Proceedings of the Eighteenth Workshop on Recent Advances in Slavonic Natural Languages Processing, RASLAN 2024}. Brno: Tribun EU, 2024, s.~3-16. ISBN~978-80-263-1835-4.

Přehled o publikaci