@inproceedings{kumar-etal-2022-bert,
title = "{BERT}-Based Sequence Labelling Approach for Dependency Parsing in {T}amil",
author = "Kumar, C S Ayush and
Maharana, Advaith and
Murali, Srinath and
B, Premjith and
Kp, Soman",
editor = "Chakravarthi, Bharathi Raja and
Priyadharshini, Ruba and
Madasamy, Anand Kumar and
Krishnamurthy, Parameswari and
Sherly, Elizabeth and
Mahesan, Sinnathamby",
booktitle = "Proceedings of the Second Workshop on Speech and Language Technologies for Dravidian Languages",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.dravidianlangtech-1.1/",
doi = "10.18653/v1/2022.dravidianlangtech-1.1",
pages = "1--8",
abstract = "Dependency parsing is a method for doing surface-level syntactic analysis on natural language texts. The scarcity of any viable tools for doing these tasks in Dravidian Languages has introduced a new line of research into these topics. This paper focuses on a novel approach that uses word-to-word dependency tagging using BERT models to improve the malt parser performance. We used Tamil, a morphologically rich and free word language. The individual words are tokenized using BERT models and the dependency relations are recognized using Machine Learning Algorithms. Oversampling algorithms such as SMOTE (Chawla et al., 2002) and ADASYN (He et al., 2008) are used to tackle data imbalance and consequently improve parsing results. The results obtained are used in the malt parser and this can be accustomed to further highlight that feature-based approaches can be used for such tasks."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kumar-etal-2022-bert">
<titleInfo>
<title>BERT-Based Sequence Labelling Approach for Dependency Parsing in Tamil</title>
</titleInfo>
<name type="personal">
<namePart type="given">C</namePart>
<namePart type="given">S</namePart>
<namePart type="given">Ayush</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Advaith</namePart>
<namePart type="family">Maharana</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Srinath</namePart>
<namePart type="family">Murali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Premjith</namePart>
<namePart type="family">B</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Soman</namePart>
<namePart type="family">Kp</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 Second Workshop on Speech and Language Technologies for Dravidian Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bharathi</namePart>
<namePart type="given">Raja</namePart>
<namePart type="family">Chakravarthi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruba</namePart>
<namePart type="family">Priyadharshini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anand</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">Madasamy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Parameswari</namePart>
<namePart type="family">Krishnamurthy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elizabeth</namePart>
<namePart type="family">Sherly</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sinnathamby</namePart>
<namePart type="family">Mahesan</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>Dependency parsing is a method for doing surface-level syntactic analysis on natural language texts. The scarcity of any viable tools for doing these tasks in Dravidian Languages has introduced a new line of research into these topics. This paper focuses on a novel approach that uses word-to-word dependency tagging using BERT models to improve the malt parser performance. We used Tamil, a morphologically rich and free word language. The individual words are tokenized using BERT models and the dependency relations are recognized using Machine Learning Algorithms. Oversampling algorithms such as SMOTE (Chawla et al., 2002) and ADASYN (He et al., 2008) are used to tackle data imbalance and consequently improve parsing results. The results obtained are used in the malt parser and this can be accustomed to further highlight that feature-based approaches can be used for such tasks.</abstract>
<identifier type="citekey">kumar-etal-2022-bert</identifier>
<identifier type="doi">10.18653/v1/2022.dravidianlangtech-1.1</identifier>
<location>
<url>https://aclanthology.org/2022.dravidianlangtech-1.1/</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>1</start>
<end>8</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BERT-Based Sequence Labelling Approach for Dependency Parsing in Tamil
%A Kumar, C. S. Ayush
%A Maharana, Advaith
%A Murali, Srinath
%A B, Premjith
%A Kp, Soman
%Y Chakravarthi, Bharathi Raja
%Y Priyadharshini, Ruba
%Y Madasamy, Anand Kumar
%Y Krishnamurthy, Parameswari
%Y Sherly, Elizabeth
%Y Mahesan, Sinnathamby
%S Proceedings of the Second Workshop on Speech and Language Technologies for Dravidian Languages
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F kumar-etal-2022-bert
%X Dependency parsing is a method for doing surface-level syntactic analysis on natural language texts. The scarcity of any viable tools for doing these tasks in Dravidian Languages has introduced a new line of research into these topics. This paper focuses on a novel approach that uses word-to-word dependency tagging using BERT models to improve the malt parser performance. We used Tamil, a morphologically rich and free word language. The individual words are tokenized using BERT models and the dependency relations are recognized using Machine Learning Algorithms. Oversampling algorithms such as SMOTE (Chawla et al., 2002) and ADASYN (He et al., 2008) are used to tackle data imbalance and consequently improve parsing results. The results obtained are used in the malt parser and this can be accustomed to further highlight that feature-based approaches can be used for such tasks.
%R 10.18653/v1/2022.dravidianlangtech-1.1
%U https://aclanthology.org/2022.dravidianlangtech-1.1/
%U https://doi.org/10.18653/v1/2022.dravidianlangtech-1.1
%P 1-8
Markdown (Informal)
[BERT-Based Sequence Labelling Approach for Dependency Parsing in Tamil](https://aclanthology.org/2022.dravidianlangtech-1.1/) (Kumar et al., DravidianLangTech 2022)
ACL