@inproceedings{ghosh-etal-2024-indicfinnlp,
title = "{I}ndic{F}in{NLP}: Financial Natural Language Processing for {I}ndian Languages",
author = "Ghosh, Sohom and
Maji, Arnab and
Narayana, Aswartha and
Naskar, Sudip Kumar",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.789",
pages = "9010--9018",
abstract = "Applications of Natural Language Processing (NLP) in the finance domain have been very popular of late. For financial NLP, (FinNLP) while various datasets exist for widely spoken languages like English and Chinese, datasets are scarce for low resource languages,particularly for Indian languages. In this paper, we address this challenges by presenting IndicFinNLP {--} a collection of 9 datasets consisting of three tasks relating to FinNLP for three Indian languages. These tasks are Exaggerated Numeral Detection, Sustainability Classification, and ESG Theme Determination of financial texts in Hindi, Bengali, and Telugu. Moreover, we release the datasets under CC BY-NC-SA 4.0 license for the benefit of the research community.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ghosh-etal-2024-indicfinnlp">
<titleInfo>
<title>IndicFinNLP: Financial Natural Language Processing for Indian Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sohom</namePart>
<namePart type="family">Ghosh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arnab</namePart>
<namePart type="family">Maji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aswartha</namePart>
<namePart type="family">Narayana</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sudip</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">Naskar</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 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</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">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</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>Applications of Natural Language Processing (NLP) in the finance domain have been very popular of late. For financial NLP, (FinNLP) while various datasets exist for widely spoken languages like English and Chinese, datasets are scarce for low resource languages,particularly for Indian languages. In this paper, we address this challenges by presenting IndicFinNLP – a collection of 9 datasets consisting of three tasks relating to FinNLP for three Indian languages. These tasks are Exaggerated Numeral Detection, Sustainability Classification, and ESG Theme Determination of financial texts in Hindi, Bengali, and Telugu. Moreover, we release the datasets under CC BY-NC-SA 4.0 license for the benefit of the research community.</abstract>
<identifier type="citekey">ghosh-etal-2024-indicfinnlp</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.789</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>9010</start>
<end>9018</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T IndicFinNLP: Financial Natural Language Processing for Indian Languages
%A Ghosh, Sohom
%A Maji, Arnab
%A Narayana, Aswartha
%A Naskar, Sudip Kumar
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F ghosh-etal-2024-indicfinnlp
%X Applications of Natural Language Processing (NLP) in the finance domain have been very popular of late. For financial NLP, (FinNLP) while various datasets exist for widely spoken languages like English and Chinese, datasets are scarce for low resource languages,particularly for Indian languages. In this paper, we address this challenges by presenting IndicFinNLP – a collection of 9 datasets consisting of three tasks relating to FinNLP for three Indian languages. These tasks are Exaggerated Numeral Detection, Sustainability Classification, and ESG Theme Determination of financial texts in Hindi, Bengali, and Telugu. Moreover, we release the datasets under CC BY-NC-SA 4.0 license for the benefit of the research community.
%U https://aclanthology.org/2024.lrec-main.789
%P 9010-9018
Markdown (Informal)
[IndicFinNLP: Financial Natural Language Processing for Indian Languages](https://aclanthology.org/2024.lrec-main.789) (Ghosh et al., LREC-COLING 2024)
ACL