@inproceedings{saetia-etal-2024-financial,
title = "Financial Product Ontology Population with Large Language Models",
author = "Saetia, Chanatip and
Phruetthiset, Jiratha and
Chalothorn, Tawunrat and
Lertsutthiwong, Monchai and
Taerungruang, Supawat and
Buabthong, Pakpoom",
editor = "Ustalov, Dmitry and
Gao, Yanjun and
Pachenko, Alexander and
Tutubalina, Elena and
Nikishina, Irina and
Ramesh, Arti and
Sakhovskiy, Andrey and
Usbeck, Ricardo and
Penn, Gerald and
Valentino, Marco",
booktitle = "Proceedings of TextGraphs-17: Graph-based Methods for Natural Language Processing",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.textgraphs-1.4",
pages = "53--60",
abstract = "Ontology population, which aims to extract structured data to enrich domain-specific ontologies from unstructured text, typically faces challenges in terms of data scarcity and linguistic complexity, particularly in specialized fields such as retail banking. In this study, we investigate the application of large language models (LLMs) to populate domain-specific ontologies of retail banking products from Thai corporate documents. We compare traditional span-based approaches to LLMs-based generative methods, with different prompting techniques. Our findings reveal that while span-based methods struggle with data scarcity and the complex linguistic structure, LLMs-based generative approaches substantially outperform, achieving a 61.05{\%} F1 score, with the most improvement coming from providing examples in the prompts. This improvement highlights the potential of LLMs for ontology population tasks, offering a scalable and efficient solution for structured information extraction in especially in low-resource language settings.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="saetia-etal-2024-financial">
<titleInfo>
<title>Financial Product Ontology Population with Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chanatip</namePart>
<namePart type="family">Saetia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiratha</namePart>
<namePart type="family">Phruetthiset</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tawunrat</namePart>
<namePart type="family">Chalothorn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Monchai</namePart>
<namePart type="family">Lertsutthiwong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Supawat</namePart>
<namePart type="family">Taerungruang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pakpoom</namePart>
<namePart type="family">Buabthong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of TextGraphs-17: Graph-based Methods for Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dmitry</namePart>
<namePart type="family">Ustalov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yanjun</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Pachenko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="family">Tutubalina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Irina</namePart>
<namePart type="family">Nikishina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arti</namePart>
<namePart type="family">Ramesh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrey</namePart>
<namePart type="family">Sakhovskiy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ricardo</namePart>
<namePart type="family">Usbeck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gerald</namePart>
<namePart type="family">Penn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Valentino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Ontology population, which aims to extract structured data to enrich domain-specific ontologies from unstructured text, typically faces challenges in terms of data scarcity and linguistic complexity, particularly in specialized fields such as retail banking. In this study, we investigate the application of large language models (LLMs) to populate domain-specific ontologies of retail banking products from Thai corporate documents. We compare traditional span-based approaches to LLMs-based generative methods, with different prompting techniques. Our findings reveal that while span-based methods struggle with data scarcity and the complex linguistic structure, LLMs-based generative approaches substantially outperform, achieving a 61.05% F1 score, with the most improvement coming from providing examples in the prompts. This improvement highlights the potential of LLMs for ontology population tasks, offering a scalable and efficient solution for structured information extraction in especially in low-resource language settings.</abstract>
<identifier type="citekey">saetia-etal-2024-financial</identifier>
<location>
<url>https://aclanthology.org/2024.textgraphs-1.4</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>53</start>
<end>60</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Financial Product Ontology Population with Large Language Models
%A Saetia, Chanatip
%A Phruetthiset, Jiratha
%A Chalothorn, Tawunrat
%A Lertsutthiwong, Monchai
%A Taerungruang, Supawat
%A Buabthong, Pakpoom
%Y Ustalov, Dmitry
%Y Gao, Yanjun
%Y Pachenko, Alexander
%Y Tutubalina, Elena
%Y Nikishina, Irina
%Y Ramesh, Arti
%Y Sakhovskiy, Andrey
%Y Usbeck, Ricardo
%Y Penn, Gerald
%Y Valentino, Marco
%S Proceedings of TextGraphs-17: Graph-based Methods for Natural Language Processing
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F saetia-etal-2024-financial
%X Ontology population, which aims to extract structured data to enrich domain-specific ontologies from unstructured text, typically faces challenges in terms of data scarcity and linguistic complexity, particularly in specialized fields such as retail banking. In this study, we investigate the application of large language models (LLMs) to populate domain-specific ontologies of retail banking products from Thai corporate documents. We compare traditional span-based approaches to LLMs-based generative methods, with different prompting techniques. Our findings reveal that while span-based methods struggle with data scarcity and the complex linguistic structure, LLMs-based generative approaches substantially outperform, achieving a 61.05% F1 score, with the most improvement coming from providing examples in the prompts. This improvement highlights the potential of LLMs for ontology population tasks, offering a scalable and efficient solution for structured information extraction in especially in low-resource language settings.
%U https://aclanthology.org/2024.textgraphs-1.4
%P 53-60
Markdown (Informal)
[Financial Product Ontology Population with Large Language Models](https://aclanthology.org/2024.textgraphs-1.4) (Saetia et al., TextGraphs-WS 2024)
ACL
- Chanatip Saetia, Jiratha Phruetthiset, Tawunrat Chalothorn, Monchai Lertsutthiwong, Supawat Taerungruang, and Pakpoom Buabthong. 2024. Financial Product Ontology Population with Large Language Models. In Proceedings of TextGraphs-17: Graph-based Methods for Natural Language Processing, pages 53–60, Bangkok, Thailand. Association for Computational Linguistics.