@inproceedings{duggenpudi-etal-2022-teluguner,
title = "{T}elugu{NER}: Leveraging Multi-Domain Named Entity Recognition with Deep Transformers",
author = "Duggenpudi, Suma Reddy and
Oota, Subba Reddy and
Marreddy, Mounika and
Mamidi, Radhika",
editor = "Louvan, Samuel and
Madotto, Andrea and
Madureira, Brielen",
booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.acl-srw.20",
doi = "10.18653/v1/2022.acl-srw.20",
pages = "262--272",
abstract = "Named Entity Recognition (NER) is a successful and well-researched problem in English due to the availability of resources. The transformer models, specifically the masked-language models (MLM), have shown remarkable performance in NER during recent times. With growing data in different online platforms, there is a need for NER in other languages too. NER remains to be underexplored in Indian languages due to the lack of resources and tools. Our contributions in this paper include (i) Two annotated NER datasets for the Telugu language in multiple domains: Newswire Dataset (ND) and Medical Dataset (MD), and we combined ND and MD to form Combined Dataset (CD) (ii) Comparison of the finetuned Telugu pretrained transformer models (BERT-Te, RoBERTa-Te, and ELECTRA-Te) with other baseline models (CRF, LSTM-CRF, and BiLSTM-CRF) (iii) Further investigation of the performance of Telugu pretrained transformer models against the multilingual models mBERT, XLM-R, and IndicBERT. We find that pretrained Telugu language models (BERT-Te and RoBERTa) outperform the existing pretrained multilingual and baseline models in NER. On a large dataset (CD) of 38,363 sentences, the BERT-Te achieves a high F1-score of 0.80 (entity-level) and 0.75 (token-level). Further, these pretrained Telugu models have shown state-of-the-art performance on various existing Telugu NER datasets. We open-source our dataset, pretrained models, and code.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="duggenpudi-etal-2022-teluguner">
<titleInfo>
<title>TeluguNER: Leveraging Multi-Domain Named Entity Recognition with Deep Transformers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Suma</namePart>
<namePart type="given">Reddy</namePart>
<namePart type="family">Duggenpudi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Subba</namePart>
<namePart type="given">Reddy</namePart>
<namePart type="family">Oota</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mounika</namePart>
<namePart type="family">Marreddy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Radhika</namePart>
<namePart type="family">Mamidi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Samuel</namePart>
<namePart type="family">Louvan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrea</namePart>
<namePart type="family">Madotto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Brielen</namePart>
<namePart type="family">Madureira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Named Entity Recognition (NER) is a successful and well-researched problem in English due to the availability of resources. The transformer models, specifically the masked-language models (MLM), have shown remarkable performance in NER during recent times. With growing data in different online platforms, there is a need for NER in other languages too. NER remains to be underexplored in Indian languages due to the lack of resources and tools. Our contributions in this paper include (i) Two annotated NER datasets for the Telugu language in multiple domains: Newswire Dataset (ND) and Medical Dataset (MD), and we combined ND and MD to form Combined Dataset (CD) (ii) Comparison of the finetuned Telugu pretrained transformer models (BERT-Te, RoBERTa-Te, and ELECTRA-Te) with other baseline models (CRF, LSTM-CRF, and BiLSTM-CRF) (iii) Further investigation of the performance of Telugu pretrained transformer models against the multilingual models mBERT, XLM-R, and IndicBERT. We find that pretrained Telugu language models (BERT-Te and RoBERTa) outperform the existing pretrained multilingual and baseline models in NER. On a large dataset (CD) of 38,363 sentences, the BERT-Te achieves a high F1-score of 0.80 (entity-level) and 0.75 (token-level). Further, these pretrained Telugu models have shown state-of-the-art performance on various existing Telugu NER datasets. We open-source our dataset, pretrained models, and code.</abstract>
<identifier type="citekey">duggenpudi-etal-2022-teluguner</identifier>
<identifier type="doi">10.18653/v1/2022.acl-srw.20</identifier>
<location>
<url>https://aclanthology.org/2022.acl-srw.20</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>262</start>
<end>272</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TeluguNER: Leveraging Multi-Domain Named Entity Recognition with Deep Transformers
%A Duggenpudi, Suma Reddy
%A Oota, Subba Reddy
%A Marreddy, Mounika
%A Mamidi, Radhika
%Y Louvan, Samuel
%Y Madotto, Andrea
%Y Madureira, Brielen
%S Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F duggenpudi-etal-2022-teluguner
%X Named Entity Recognition (NER) is a successful and well-researched problem in English due to the availability of resources. The transformer models, specifically the masked-language models (MLM), have shown remarkable performance in NER during recent times. With growing data in different online platforms, there is a need for NER in other languages too. NER remains to be underexplored in Indian languages due to the lack of resources and tools. Our contributions in this paper include (i) Two annotated NER datasets for the Telugu language in multiple domains: Newswire Dataset (ND) and Medical Dataset (MD), and we combined ND and MD to form Combined Dataset (CD) (ii) Comparison of the finetuned Telugu pretrained transformer models (BERT-Te, RoBERTa-Te, and ELECTRA-Te) with other baseline models (CRF, LSTM-CRF, and BiLSTM-CRF) (iii) Further investigation of the performance of Telugu pretrained transformer models against the multilingual models mBERT, XLM-R, and IndicBERT. We find that pretrained Telugu language models (BERT-Te and RoBERTa) outperform the existing pretrained multilingual and baseline models in NER. On a large dataset (CD) of 38,363 sentences, the BERT-Te achieves a high F1-score of 0.80 (entity-level) and 0.75 (token-level). Further, these pretrained Telugu models have shown state-of-the-art performance on various existing Telugu NER datasets. We open-source our dataset, pretrained models, and code.
%R 10.18653/v1/2022.acl-srw.20
%U https://aclanthology.org/2022.acl-srw.20
%U https://doi.org/10.18653/v1/2022.acl-srw.20
%P 262-272
Markdown (Informal)
[TeluguNER: Leveraging Multi-Domain Named Entity Recognition with Deep Transformers](https://aclanthology.org/2022.acl-srw.20) (Duggenpudi et al., ACL 2022)
ACL