@inproceedings{kao-etal-2024-imntpu,
title = "{IMNTPU} at {ML}-{ESG}-3: Transformer Language Models for Multi-Lingual {ESG} Impact Type and Duration Classification",
author = "Kao, Yu Han and
Nataraj, Vidhya and
Wang, Ting-Chi and
Zheng, Yu-Jyun and
Liu, Hsiao-Chuan and
Liao, Wen-Hsuan and
Tsai, Chia-Tung and
Day, Min-Yuh",
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",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.finnlp-1.23",
pages = "228--233",
abstract = "Our team participated in the multi-lingual Environmental, Social, and Governance (ESG) classification task, focusing on datasets in three languages: English, French, and Japanese. This study leverages Pre-trained Language Models (PLMs), with a particular emphasis on the Bidirectional Encoder Representations from Transformers (BERT) framework, to analyze sentence and document structures across these varied linguistic datasets. The team{'}s experimentation with diverse PLM-based network designs facilitated a nuanced comparative analysis within this multi-lingual context. For each language-specific dataset, different BERT-based transformer models were trained and evaluated. Notably, in the experimental results, the RoBERTa-Base model emerged as the most effective in official evaluation, particularly in the English dataset, achieving a micro-F1 score of 58.82 {\%}, thereby demonstrating superior performance in classifying ESG impact levels. This research highlights the adaptability and effectiveness of PLMs in tackling the complexities of multi-lingual ESG classification tasks, underscoring the exceptional performance of the Roberta Base model in processing English-language data.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kao-etal-2024-imntpu">
<titleInfo>
<title>IMNTPU at ML-ESG-3: Transformer Language Models for Multi-Lingual ESG Impact Type and Duration Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="given">Han</namePart>
<namePart type="family">Kao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vidhya</namePart>
<namePart type="family">Nataraj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ting-Chi</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu-Jyun</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsiao-Chuan</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wen-Hsuan</namePart>
<namePart type="family">Liao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chia-Tung</namePart>
<namePart type="family">Tsai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yuh</namePart>
<namePart type="family">Day</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</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>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Our team participated in the multi-lingual Environmental, Social, and Governance (ESG) classification task, focusing on datasets in three languages: English, French, and Japanese. This study leverages Pre-trained Language Models (PLMs), with a particular emphasis on the Bidirectional Encoder Representations from Transformers (BERT) framework, to analyze sentence and document structures across these varied linguistic datasets. The team’s experimentation with diverse PLM-based network designs facilitated a nuanced comparative analysis within this multi-lingual context. For each language-specific dataset, different BERT-based transformer models were trained and evaluated. Notably, in the experimental results, the RoBERTa-Base model emerged as the most effective in official evaluation, particularly in the English dataset, achieving a micro-F1 score of 58.82 %, thereby demonstrating superior performance in classifying ESG impact levels. This research highlights the adaptability and effectiveness of PLMs in tackling the complexities of multi-lingual ESG classification tasks, underscoring the exceptional performance of the Roberta Base model in processing English-language data.</abstract>
<identifier type="citekey">kao-etal-2024-imntpu</identifier>
<location>
<url>https://aclanthology.org/2024.finnlp-1.23</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>228</start>
<end>233</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T IMNTPU at ML-ESG-3: Transformer Language Models for Multi-Lingual ESG Impact Type and Duration Classification
%A Kao, Yu Han
%A Nataraj, Vidhya
%A Wang, Ting-Chi
%A Zheng, Yu-Jyun
%A Liu, Hsiao-Chuan
%A Liao, Wen-Hsuan
%A Tsai, Chia-Tung
%A Day, Min-Yuh
%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
%D 2024
%8 May
%I Association for Computational Linguistics
%C Torino, Italia
%F kao-etal-2024-imntpu
%X Our team participated in the multi-lingual Environmental, Social, and Governance (ESG) classification task, focusing on datasets in three languages: English, French, and Japanese. This study leverages Pre-trained Language Models (PLMs), with a particular emphasis on the Bidirectional Encoder Representations from Transformers (BERT) framework, to analyze sentence and document structures across these varied linguistic datasets. The team’s experimentation with diverse PLM-based network designs facilitated a nuanced comparative analysis within this multi-lingual context. For each language-specific dataset, different BERT-based transformer models were trained and evaluated. Notably, in the experimental results, the RoBERTa-Base model emerged as the most effective in official evaluation, particularly in the English dataset, achieving a micro-F1 score of 58.82 %, thereby demonstrating superior performance in classifying ESG impact levels. This research highlights the adaptability and effectiveness of PLMs in tackling the complexities of multi-lingual ESG classification tasks, underscoring the exceptional performance of the Roberta Base model in processing English-language data.
%U https://aclanthology.org/2024.finnlp-1.23
%P 228-233
Markdown (Informal)
[IMNTPU at ML-ESG-3: Transformer Language Models for Multi-Lingual ESG Impact Type and Duration Classification](https://aclanthology.org/2024.finnlp-1.23) (Kao et al., FinNLP 2024)
ACL
- Yu Han Kao, Vidhya Nataraj, Ting-Chi Wang, Yu-Jyun Zheng, Hsiao-Chuan Liu, Wen-Hsuan Liao, Chia-Tung Tsai, and Min-Yuh Day. 2024. IMNTPU at ML-ESG-3: Transformer Language Models for Multi-Lingual ESG Impact Type and Duration Classification. 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, pages 228–233, Torino, Italia. Association for Computational Linguistics.