@inproceedings{sai-rishith-reddy-etal-2023-enhancing,
title = "Enhancing {T}elugu Part-of-Speech Tagging with Deep Sequential Models and Multilingual Embeddings",
author = "Sai Rishith Reddy, Mangamuru and
Sai Prashanth, Karnati and
Bala Karthikeya, Sajja and
Divith, Phogat and
Premjith, B.",
editor = "Jyoti, D. Pawar and
Sobha, Lalitha Devi",
booktitle = "Proceedings of the 20th International Conference on Natural Language Processing (ICON)",
month = dec,
year = "2023",
address = "Goa University, Goa, India",
publisher = "NLP Association of India (NLPAI)",
url = "https://aclanthology.org/2023.icon-1.77",
pages = "760--765",
abstract = "Part-of-speech (POS) tagging is a fundamental task in natural language processing (NLP) that involves assigning grammatical categories to words in a sentence. In this study, we investigate the application of deep sequential models for POS tagging of Telugu, a low-resource Dravidian language with rich morphology. We use the Universal dependencies dataset for this research and explore various deep learning architectures, including Recurrent Neural Networks (RNNs), Long Short-Term Memory (LSTM) networks, Gated Recurrent Units (GRUs), and their stacked variants for POS tagging. Additionally, we utilize multilingual BERT embeddings and indicBERT embeddings to capture contextual information from the input sequences. Our experiments demonstrate that stacked LSTM with multilingual BERT embeddings achieves the highest performance, outperforming other approaches and attaining an F1 score of 0.8812. These findings suggest that deep sequential models, particularly stacked LSTMs with multilingual BERT embeddings, are effective tools for POS tagging in Telugu.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sai-rishith-reddy-etal-2023-enhancing">
<titleInfo>
<title>Enhancing Telugu Part-of-Speech Tagging with Deep Sequential Models and Multilingual Embeddings</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mangamuru</namePart>
<namePart type="family">Sai Rishith Reddy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karnati</namePart>
<namePart type="family">Sai Prashanth</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sajja</namePart>
<namePart type="family">Bala Karthikeya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Phogat</namePart>
<namePart type="family">Divith</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">B</namePart>
<namePart type="family">Premjith</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 20th International Conference on Natural Language Processing (ICON)</title>
</titleInfo>
<name type="personal">
<namePart type="given">D</namePart>
<namePart type="given">Pawar</namePart>
<namePart type="family">Jyoti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lalitha</namePart>
<namePart type="given">Devi</namePart>
<namePart type="family">Sobha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>NLP Association of India (NLPAI)</publisher>
<place>
<placeTerm type="text">Goa University, Goa, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Part-of-speech (POS) tagging is a fundamental task in natural language processing (NLP) that involves assigning grammatical categories to words in a sentence. In this study, we investigate the application of deep sequential models for POS tagging of Telugu, a low-resource Dravidian language with rich morphology. We use the Universal dependencies dataset for this research and explore various deep learning architectures, including Recurrent Neural Networks (RNNs), Long Short-Term Memory (LSTM) networks, Gated Recurrent Units (GRUs), and their stacked variants for POS tagging. Additionally, we utilize multilingual BERT embeddings and indicBERT embeddings to capture contextual information from the input sequences. Our experiments demonstrate that stacked LSTM with multilingual BERT embeddings achieves the highest performance, outperforming other approaches and attaining an F1 score of 0.8812. These findings suggest that deep sequential models, particularly stacked LSTMs with multilingual BERT embeddings, are effective tools for POS tagging in Telugu.</abstract>
<identifier type="citekey">sai-rishith-reddy-etal-2023-enhancing</identifier>
<location>
<url>https://aclanthology.org/2023.icon-1.77</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>760</start>
<end>765</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Enhancing Telugu Part-of-Speech Tagging with Deep Sequential Models and Multilingual Embeddings
%A Sai Rishith Reddy, Mangamuru
%A Sai Prashanth, Karnati
%A Bala Karthikeya, Sajja
%A Divith, Phogat
%A Premjith, B.
%Y Jyoti, D. Pawar
%Y Sobha, Lalitha Devi
%S Proceedings of the 20th International Conference on Natural Language Processing (ICON)
%D 2023
%8 December
%I NLP Association of India (NLPAI)
%C Goa University, Goa, India
%F sai-rishith-reddy-etal-2023-enhancing
%X Part-of-speech (POS) tagging is a fundamental task in natural language processing (NLP) that involves assigning grammatical categories to words in a sentence. In this study, we investigate the application of deep sequential models for POS tagging of Telugu, a low-resource Dravidian language with rich morphology. We use the Universal dependencies dataset for this research and explore various deep learning architectures, including Recurrent Neural Networks (RNNs), Long Short-Term Memory (LSTM) networks, Gated Recurrent Units (GRUs), and their stacked variants for POS tagging. Additionally, we utilize multilingual BERT embeddings and indicBERT embeddings to capture contextual information from the input sequences. Our experiments demonstrate that stacked LSTM with multilingual BERT embeddings achieves the highest performance, outperforming other approaches and attaining an F1 score of 0.8812. These findings suggest that deep sequential models, particularly stacked LSTMs with multilingual BERT embeddings, are effective tools for POS tagging in Telugu.
%U https://aclanthology.org/2023.icon-1.77
%P 760-765
Markdown (Informal)
[Enhancing Telugu Part-of-Speech Tagging with Deep Sequential Models and Multilingual Embeddings](https://aclanthology.org/2023.icon-1.77) (Sai Rishith Reddy et al., ICON 2023)
ACL