@inproceedings{winatmoko-septiandri-2023-risk,
title = "The Risk and Opportunity of Data Augmentation and Translation for {ESG} News Impact Identification with Language Models",
author = "Winatmoko, Yosef Ardhito and
Septiandri, Ali",
editor = "Chen, Chung-Chi and
Huang, Hen-Hsen and
Takamura, Hiroya and
Chen, Hsin-Hsi and
Sakaji, Hiroki and
Izumi, Kiyoshi",
booktitle = "Proceedings of the Sixth Workshop on Financial Technology and Natural Language Processing",
month = nov,
year = "2023",
address = "Bali, Indonesia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.finnlp-2.10",
doi = "10.18653/v1/2023.finnlp-2.10",
pages = "66--71",
abstract = "This paper presents our findings in the ML-ESG-2 task, which focused on classifying a news snippet of various languages as {``}Risk{''} or {``}Opportunity{''} in the ESG (Environmental, Social, and Governance) context. We experimented with data augmentation and translation facilitated by Large Language Models (LLM). We found that augmenting the English dataset did not help to improve the performance. By fine-tuning RoBERTa models with the original data, we achieved the top position for the English and second place for the French task. In contrast, we could achieve comparable results on the French dataset by solely using the English translation, securing the third position for the French task with only marginal F1 differences to the second-place model.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="winatmoko-septiandri-2023-risk">
<titleInfo>
<title>The Risk and Opportunity of Data Augmentation and Translation for ESG News Impact Identification with Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yosef</namePart>
<namePart type="given">Ardhito</namePart>
<namePart type="family">Winatmoko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ali</namePart>
<namePart type="family">Septiandri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth Workshop on Financial Technology 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">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>
<name type="personal">
<namePart type="given">Hiroki</namePart>
<namePart type="family">Sakaji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kiyoshi</namePart>
<namePart type="family">Izumi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bali, Indonesia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents our findings in the ML-ESG-2 task, which focused on classifying a news snippet of various languages as “Risk” or “Opportunity” in the ESG (Environmental, Social, and Governance) context. We experimented with data augmentation and translation facilitated by Large Language Models (LLM). We found that augmenting the English dataset did not help to improve the performance. By fine-tuning RoBERTa models with the original data, we achieved the top position for the English and second place for the French task. In contrast, we could achieve comparable results on the French dataset by solely using the English translation, securing the third position for the French task with only marginal F1 differences to the second-place model.</abstract>
<identifier type="citekey">winatmoko-septiandri-2023-risk</identifier>
<identifier type="doi">10.18653/v1/2023.finnlp-2.10</identifier>
<location>
<url>https://aclanthology.org/2023.finnlp-2.10</url>
</location>
<part>
<date>2023-11</date>
<extent unit="page">
<start>66</start>
<end>71</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Risk and Opportunity of Data Augmentation and Translation for ESG News Impact Identification with Language Models
%A Winatmoko, Yosef Ardhito
%A Septiandri, Ali
%Y Chen, Chung-Chi
%Y Huang, Hen-Hsen
%Y Takamura, Hiroya
%Y Chen, Hsin-Hsi
%Y Sakaji, Hiroki
%Y Izumi, Kiyoshi
%S Proceedings of the Sixth Workshop on Financial Technology and Natural Language Processing
%D 2023
%8 November
%I Association for Computational Linguistics
%C Bali, Indonesia
%F winatmoko-septiandri-2023-risk
%X This paper presents our findings in the ML-ESG-2 task, which focused on classifying a news snippet of various languages as “Risk” or “Opportunity” in the ESG (Environmental, Social, and Governance) context. We experimented with data augmentation and translation facilitated by Large Language Models (LLM). We found that augmenting the English dataset did not help to improve the performance. By fine-tuning RoBERTa models with the original data, we achieved the top position for the English and second place for the French task. In contrast, we could achieve comparable results on the French dataset by solely using the English translation, securing the third position for the French task with only marginal F1 differences to the second-place model.
%R 10.18653/v1/2023.finnlp-2.10
%U https://aclanthology.org/2023.finnlp-2.10
%U https://doi.org/10.18653/v1/2023.finnlp-2.10
%P 66-71
Markdown (Informal)
[The Risk and Opportunity of Data Augmentation and Translation for ESG News Impact Identification with Language Models](https://aclanthology.org/2023.finnlp-2.10) (Winatmoko & Septiandri, FinNLP-WS 2023)
ACL