@inproceedings{jorgensen-etal-2023-multifin,
title = "{M}ulti{F}in: A Dataset for Multilingual Financial {NLP}",
author = "J{\o}rgensen, Rasmus and
Brandt, Oliver and
Hartmann, Mareike and
Dai, Xiang and
Igel, Christian and
Elliott, Desmond",
editor = "Vlachos, Andreas and
Augenstein, Isabelle",
booktitle = "Findings of the Association for Computational Linguistics: EACL 2023",
month = may,
year = "2023",
address = "Dubrovnik, Croatia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-eacl.66",
doi = "10.18653/v1/2023.findings-eacl.66",
pages = "894--909",
abstract = "Financial information is generated and distributed across the world, resulting in a vast amount of domain-specific multilingual data. Multilingual models adapted to the financial domain would ease deployment when an organization needs to work with multiple languages on a regular basis. For the development and evaluation of such models, there is a need for multilingual financial language processing datasets. We describe MultiFin {--} a publicly available financial dataset consisting of real-world article headlines covering 15 languages across different writing systems and language families. The dataset consists of hierarchical label structure providing two classification tasks: multi-label and multi-class. We develop our annotation schema based on a real-world application and annotate our dataset using both {`}label by native-speaker{'} and {`}translate-then-label{'} approaches. The evaluation of several popular multilingual models, e.g., mBERT, XLM-R, and mT5, show that although decent accuracy can be achieved in high-resource languages, there is substantial room for improvement in low-resource languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jorgensen-etal-2023-multifin">
<titleInfo>
<title>MultiFin: A Dataset for Multilingual Financial NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rasmus</namePart>
<namePart type="family">Jørgensen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oliver</namePart>
<namePart type="family">Brandt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mareike</namePart>
<namePart type="family">Hartmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiang</namePart>
<namePart type="family">Dai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christian</namePart>
<namePart type="family">Igel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EACL 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Vlachos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isabelle</namePart>
<namePart type="family">Augenstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dubrovnik, Croatia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Financial information is generated and distributed across the world, resulting in a vast amount of domain-specific multilingual data. Multilingual models adapted to the financial domain would ease deployment when an organization needs to work with multiple languages on a regular basis. For the development and evaluation of such models, there is a need for multilingual financial language processing datasets. We describe MultiFin – a publicly available financial dataset consisting of real-world article headlines covering 15 languages across different writing systems and language families. The dataset consists of hierarchical label structure providing two classification tasks: multi-label and multi-class. We develop our annotation schema based on a real-world application and annotate our dataset using both ‘label by native-speaker’ and ‘translate-then-label’ approaches. The evaluation of several popular multilingual models, e.g., mBERT, XLM-R, and mT5, show that although decent accuracy can be achieved in high-resource languages, there is substantial room for improvement in low-resource languages.</abstract>
<identifier type="citekey">jorgensen-etal-2023-multifin</identifier>
<identifier type="doi">10.18653/v1/2023.findings-eacl.66</identifier>
<location>
<url>https://aclanthology.org/2023.findings-eacl.66</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>894</start>
<end>909</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MultiFin: A Dataset for Multilingual Financial NLP
%A Jørgensen, Rasmus
%A Brandt, Oliver
%A Hartmann, Mareike
%A Dai, Xiang
%A Igel, Christian
%A Elliott, Desmond
%Y Vlachos, Andreas
%Y Augenstein, Isabelle
%S Findings of the Association for Computational Linguistics: EACL 2023
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F jorgensen-etal-2023-multifin
%X Financial information is generated and distributed across the world, resulting in a vast amount of domain-specific multilingual data. Multilingual models adapted to the financial domain would ease deployment when an organization needs to work with multiple languages on a regular basis. For the development and evaluation of such models, there is a need for multilingual financial language processing datasets. We describe MultiFin – a publicly available financial dataset consisting of real-world article headlines covering 15 languages across different writing systems and language families. The dataset consists of hierarchical label structure providing two classification tasks: multi-label and multi-class. We develop our annotation schema based on a real-world application and annotate our dataset using both ‘label by native-speaker’ and ‘translate-then-label’ approaches. The evaluation of several popular multilingual models, e.g., mBERT, XLM-R, and mT5, show that although decent accuracy can be achieved in high-resource languages, there is substantial room for improvement in low-resource languages.
%R 10.18653/v1/2023.findings-eacl.66
%U https://aclanthology.org/2023.findings-eacl.66
%U https://doi.org/10.18653/v1/2023.findings-eacl.66
%P 894-909
Markdown (Informal)
[MultiFin: A Dataset for Multilingual Financial NLP](https://aclanthology.org/2023.findings-eacl.66) (Jørgensen et al., Findings 2023)
ACL
- Rasmus Jørgensen, Oliver Brandt, Mareike Hartmann, Xiang Dai, Christian Igel, and Desmond Elliott. 2023. MultiFin: A Dataset for Multilingual Financial NLP. In Findings of the Association for Computational Linguistics: EACL 2023, pages 894–909, Dubrovnik, Croatia. Association for Computational Linguistics.