@inproceedings{sharma-etal-2024-improving,
title = "Improving Cross-Lingual {CSR} Classification Using Pretrained Transformers with Variable Selection Networks and Data Augmentation",
author = "Sharma, Shubham and
Janbandhu, Himanshu and
Chopra, Ankush",
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-1.34",
pages = "306--318",
abstract = "This paper describes our submission to the Cross-Lingual Classification of Corporate Social Responsibility (CSR) Themes and Topics shared task, aiming to identify themes and fine-grained topics present in news articles. Classifying news articles poses several challenges, including limited training data, noisy articles, and longer context length. In this paper, we explore the potential of using pretrained transformer models to classify news articles into CSR themes and fine-grained topics. We propose two different approaches for these tasks. For multi-class classification of CSR themes, we suggest using a pretrained multi-lingual encoder-based model like microsoft/mDeBERTa-v3-base, along with a variable selection network to classify the article into CSR themes. To identify all fine-grained topics in each article, we propose using a pretrained encoder-based model like Longformer, which offers a higher context length. We employ chunking-based inference to avoid information loss in inference and experimented with using different parts and manifestation of original article for training and inference.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sharma-etal-2024-improving">
<titleInfo>
<title>Improving Cross-Lingual CSR Classification Using Pretrained Transformers with Variable Selection Networks and Data Augmentation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shubham</namePart>
<namePart type="family">Sharma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Himanshu</namePart>
<namePart type="family">Janbandhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ankush</namePart>
<namePart type="family">Chopra</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>This paper describes our submission to the Cross-Lingual Classification of Corporate Social Responsibility (CSR) Themes and Topics shared task, aiming to identify themes and fine-grained topics present in news articles. Classifying news articles poses several challenges, including limited training data, noisy articles, and longer context length. In this paper, we explore the potential of using pretrained transformer models to classify news articles into CSR themes and fine-grained topics. We propose two different approaches for these tasks. For multi-class classification of CSR themes, we suggest using a pretrained multi-lingual encoder-based model like microsoft/mDeBERTa-v3-base, along with a variable selection network to classify the article into CSR themes. To identify all fine-grained topics in each article, we propose using a pretrained encoder-based model like Longformer, which offers a higher context length. We employ chunking-based inference to avoid information loss in inference and experimented with using different parts and manifestation of original article for training and inference.</abstract>
<identifier type="citekey">sharma-etal-2024-improving</identifier>
<location>
<url>https://aclanthology.org/2024.finnlp-1.34</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>306</start>
<end>318</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving Cross-Lingual CSR Classification Using Pretrained Transformers with Variable Selection Networks and Data Augmentation
%A Sharma, Shubham
%A Janbandhu, Himanshu
%A Chopra, Ankush
%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 sharma-etal-2024-improving
%X This paper describes our submission to the Cross-Lingual Classification of Corporate Social Responsibility (CSR) Themes and Topics shared task, aiming to identify themes and fine-grained topics present in news articles. Classifying news articles poses several challenges, including limited training data, noisy articles, and longer context length. In this paper, we explore the potential of using pretrained transformer models to classify news articles into CSR themes and fine-grained topics. We propose two different approaches for these tasks. For multi-class classification of CSR themes, we suggest using a pretrained multi-lingual encoder-based model like microsoft/mDeBERTa-v3-base, along with a variable selection network to classify the article into CSR themes. To identify all fine-grained topics in each article, we propose using a pretrained encoder-based model like Longformer, which offers a higher context length. We employ chunking-based inference to avoid information loss in inference and experimented with using different parts and manifestation of original article for training and inference.
%U https://aclanthology.org/2024.finnlp-1.34
%P 306-318
Markdown (Informal)
[Improving Cross-Lingual CSR Classification Using Pretrained Transformers with Variable Selection Networks and Data Augmentation](https://aclanthology.org/2024.finnlp-1.34) (Sharma et al., FinNLP 2024)
ACL