@inproceedings{li-etal-2024-evaluating-multilingual,
title = "Evaluating Multilingual Language Models for Cross-Lingual {ESG} Issue Identification",
author = "Li, Wing Yan and
Chersoni, Emmanuele and
Ngai, Cindy Sing Bik",
editor = "Chen, Chung-Chi and
Liu, Xiaomo and
Hahn, Udo and
Nourbakhsh, Armineh and
Ma, Zhiqiang and
Smiley, Charese and
Hoste, Veronique and
Das, Sanjiv Ranjan and
Li, Manling and
Ghassemi, Mohammad and
Huang, Hen-Hsen and
Takamura, Hiroya and
Chen, Hsin-Hsi",
booktitle = "Proceedings of the Joint Workshop of the 7th Financial Technology and Natural Language Processing, the 5th Knowledge Discovery from Unstructured Data in Financial Services, and the 4th Workshop on Economics and Natural Language Processing @ LREC-COLING 2024",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.finnlp-1.6",
pages = "50--58",
abstract = "The automation of information extraction from ESG reports has recently become a topic of increasing interest in the Natural Language Processing community. While such information is highly relevant for socially responsible investments, identifying the specific issues discussed in a corporate social responsibility report is one of the first steps in an information extraction pipeline. In this paper, we evaluate methods for tackling the Multilingual Environmental, Social and Governance (ESG) Issue Identification Task. Our experiments use existing datasets in English, French and Chinese with a unified label set. Leveraging multilingual language models, we compare two approaches that are commonly adopted for the given task: off-the-shelf and fine-tuning. We show that fine-tuning models end-to-end is more robust than off-the-shelf methods. Additionally, translating text into the same language has negligible performance benefits.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2024-evaluating-multilingual">
<titleInfo>
<title>Evaluating Multilingual Language Models for Cross-Lingual ESG Issue Identification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wing</namePart>
<namePart type="given">Yan</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emmanuele</namePart>
<namePart type="family">Chersoni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cindy</namePart>
<namePart type="given">Sing</namePart>
<namePart type="given">Bik</namePart>
<namePart type="family">Ngai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Joint Workshop of the 7th Financial Technology and Natural Language Processing, the 5th Knowledge Discovery from Unstructured Data in Financial Services, and the 4th Workshop on Economics and Natural Language Processing @ LREC-COLING 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chung-Chi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaomo</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Udo</namePart>
<namePart type="family">Hahn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Armineh</namePart>
<namePart type="family">Nourbakhsh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiqiang</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Charese</namePart>
<namePart type="family">Smiley</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sanjiv</namePart>
<namePart type="given">Ranjan</namePart>
<namePart type="family">Das</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manling</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="family">Ghassemi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hen-Hsen</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hiroya</namePart>
<namePart type="family">Takamura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Hsi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The automation of information extraction from ESG reports has recently become a topic of increasing interest in the Natural Language Processing community. While such information is highly relevant for socially responsible investments, identifying the specific issues discussed in a corporate social responsibility report is one of the first steps in an information extraction pipeline. In this paper, we evaluate methods for tackling the Multilingual Environmental, Social and Governance (ESG) Issue Identification Task. Our experiments use existing datasets in English, French and Chinese with a unified label set. Leveraging multilingual language models, we compare two approaches that are commonly adopted for the given task: off-the-shelf and fine-tuning. We show that fine-tuning models end-to-end is more robust than off-the-shelf methods. Additionally, translating text into the same language has negligible performance benefits.</abstract>
<identifier type="citekey">li-etal-2024-evaluating-multilingual</identifier>
<location>
<url>https://aclanthology.org/2024.finnlp-1.6</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>50</start>
<end>58</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluating Multilingual Language Models for Cross-Lingual ESG Issue Identification
%A Li, Wing Yan
%A Chersoni, Emmanuele
%A Ngai, Cindy Sing Bik
%Y Chen, Chung-Chi
%Y Liu, Xiaomo
%Y Hahn, Udo
%Y Nourbakhsh, Armineh
%Y Ma, Zhiqiang
%Y Smiley, Charese
%Y Hoste, Veronique
%Y Das, Sanjiv Ranjan
%Y Li, Manling
%Y Ghassemi, Mohammad
%Y Huang, Hen-Hsen
%Y Takamura, Hiroya
%Y Chen, Hsin-Hsi
%S Proceedings of the Joint Workshop of the 7th Financial Technology and Natural Language Processing, the 5th Knowledge Discovery from Unstructured Data in Financial Services, and the 4th Workshop on Economics and Natural Language Processing @ LREC-COLING 2024
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F li-etal-2024-evaluating-multilingual
%X The automation of information extraction from ESG reports has recently become a topic of increasing interest in the Natural Language Processing community. While such information is highly relevant for socially responsible investments, identifying the specific issues discussed in a corporate social responsibility report is one of the first steps in an information extraction pipeline. In this paper, we evaluate methods for tackling the Multilingual Environmental, Social and Governance (ESG) Issue Identification Task. Our experiments use existing datasets in English, French and Chinese with a unified label set. Leveraging multilingual language models, we compare two approaches that are commonly adopted for the given task: off-the-shelf and fine-tuning. We show that fine-tuning models end-to-end is more robust than off-the-shelf methods. Additionally, translating text into the same language has negligible performance benefits.
%U https://aclanthology.org/2024.finnlp-1.6
%P 50-58
Markdown (Informal)
[Evaluating Multilingual Language Models for Cross-Lingual ESG Issue Identification](https://aclanthology.org/2024.finnlp-1.6) (Li et al., FinNLP-WS 2024)
ACL
- Wing Yan Li, Emmanuele Chersoni, and Cindy Sing Bik Ngai. 2024. Evaluating Multilingual Language Models for Cross-Lingual ESG Issue Identification. In Proceedings of the Joint Workshop of the 7th Financial Technology and Natural Language Processing, the 5th Knowledge Discovery from Unstructured Data in Financial Services, and the 4th Workshop on Economics and Natural Language Processing @ LREC-COLING 2024, pages 50–58, Torino, Italia. ELRA and ICCL.