@inproceedings{bahad-etal-2024-fine,
title = "Fine-tuning Pre-trained Named Entity Recognition Models For {I}ndian Languages",
author = "Bahad, Sankalp and
Mishra, Pruthwik and
Krishnamurthy, Parameswari and
Sharma, Dipti",
editor = "Cao, Yang (Trista) and
Papadimitriou, Isabel and
Ovalle, Anaelia",
booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.naacl-srw.9",
pages = "75--82",
abstract = "Named Entity Recognition (NER) is a use-ful component in Natural Language Process-ing (NLP) applications. It is used in varioustasks such as Machine Translation, Summa-rization, Information Retrieval, and Question-Answering systems. The research on NER iscentered around English and some other ma-jor languages, whereas limited attention hasbeen given to Indian languages. We analyze thechallenges and propose techniques that can betailored for Multilingual Named Entity Recog-nition for Indian Languages. We present a hu-man annotated named entity corpora of ∼40Ksentences for 4 Indian languages from two ofthe major Indian language families. Addition-ally, we show the transfer learning capabilitiesof pre-trained transformer models from a highresource language to multiple low resource lan-guages through a series of experiments. Wealso present a multilingual model fine-tunedon our dataset, which achieves an F1 score of∼0.80 on our dataset on average. We achievecomparable performance on completely unseenbenchmark datasets for Indian languages whichaffirms the usability of our model.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bahad-etal-2024-fine">
<titleInfo>
<title>Fine-tuning Pre-trained Named Entity Recognition Models For Indian Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sankalp</namePart>
<namePart type="family">Bahad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pruthwik</namePart>
<namePart type="family">Mishra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Parameswari</namePart>
<namePart type="family">Krishnamurthy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dipti</namePart>
<namePart type="family">Sharma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="given">(Trista)</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isabel</namePart>
<namePart type="family">Papadimitriou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anaelia</namePart>
<namePart type="family">Ovalle</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Named Entity Recognition (NER) is a use-ful component in Natural Language Process-ing (NLP) applications. It is used in varioustasks such as Machine Translation, Summa-rization, Information Retrieval, and Question-Answering systems. The research on NER iscentered around English and some other ma-jor languages, whereas limited attention hasbeen given to Indian languages. We analyze thechallenges and propose techniques that can betailored for Multilingual Named Entity Recog-nition for Indian Languages. We present a hu-man annotated named entity corpora of ∼40Ksentences for 4 Indian languages from two ofthe major Indian language families. Addition-ally, we show the transfer learning capabilitiesof pre-trained transformer models from a highresource language to multiple low resource lan-guages through a series of experiments. Wealso present a multilingual model fine-tunedon our dataset, which achieves an F1 score of∼0.80 on our dataset on average. We achievecomparable performance on completely unseenbenchmark datasets for Indian languages whichaffirms the usability of our model.</abstract>
<identifier type="citekey">bahad-etal-2024-fine</identifier>
<location>
<url>https://aclanthology.org/2024.naacl-srw.9</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>75</start>
<end>82</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Fine-tuning Pre-trained Named Entity Recognition Models For Indian Languages
%A Bahad, Sankalp
%A Mishra, Pruthwik
%A Krishnamurthy, Parameswari
%A Sharma, Dipti
%Y Cao, Yang (Trista)
%Y Papadimitriou, Isabel
%Y Ovalle, Anaelia
%S Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F bahad-etal-2024-fine
%X Named Entity Recognition (NER) is a use-ful component in Natural Language Process-ing (NLP) applications. It is used in varioustasks such as Machine Translation, Summa-rization, Information Retrieval, and Question-Answering systems. The research on NER iscentered around English and some other ma-jor languages, whereas limited attention hasbeen given to Indian languages. We analyze thechallenges and propose techniques that can betailored for Multilingual Named Entity Recog-nition for Indian Languages. We present a hu-man annotated named entity corpora of ∼40Ksentences for 4 Indian languages from two ofthe major Indian language families. Addition-ally, we show the transfer learning capabilitiesof pre-trained transformer models from a highresource language to multiple low resource lan-guages through a series of experiments. Wealso present a multilingual model fine-tunedon our dataset, which achieves an F1 score of∼0.80 on our dataset on average. We achievecomparable performance on completely unseenbenchmark datasets for Indian languages whichaffirms the usability of our model.
%U https://aclanthology.org/2024.naacl-srw.9
%P 75-82
Markdown (Informal)
[Fine-tuning Pre-trained Named Entity Recognition Models For Indian Languages](https://aclanthology.org/2024.naacl-srw.9) (Bahad et al., NAACL 2024)
ACL
- Sankalp Bahad, Pruthwik Mishra, Parameswari Krishnamurthy, and Dipti Sharma. 2024. Fine-tuning Pre-trained Named Entity Recognition Models For Indian Languages. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop), pages 75–82, Mexico City, Mexico. Association for Computational Linguistics.