@inproceedings{sarveswaran-dias-2020-thamizhiudp,
title = "{T}hamizhi{UD}p: A Dependency Parser for {T}amil",
author = "Sarveswaran, Kengatharaiyer and
Dias, Gihan",
editor = "Bhattacharyya, Pushpak and
Sharma, Dipti Misra and
Sangal, Rajeev",
booktitle = "Proceedings of the 17th International Conference on Natural Language Processing (ICON)",
month = dec,
year = "2020",
address = "Indian Institute of Technology Patna, Patna, India",
publisher = "NLP Association of India (NLPAI)",
url = "https://aclanthology.org/2020.icon-main.26",
pages = "200--207",
abstract = "This paper describes how we developed a neural-based dependency parser, namely ThamizhiUDp, which provides a complete pipeline for the dependency parsing of the Tamil language text using Universal Dependency formalism. We have considered the phases of the dependency parsing pipeline and identified tools and resources in each of these phases to improve the accuracy and to tackle data scarcity. ThamizhiUDp uses Stanza for tokenisation and lemmatisation, ThamizhiPOSt and ThamizhiMorph for generating Part of Speech (POS) and Morphological annotations, and uuparser with multilingual training for dependency parsing. ThamizhiPOSt is our POS tagger, which is based on the Stanza, trained with Amrita POS-tagged corpus. It is the current state-of-the-art in Tamil POS tagging with an F1 score of 93.27. Our morphological analyzer, ThamizhiMorph is a rule-based system with a very good coverage of Tamil. Our dependency parser ThamizhiUDp was trained using multilingual data. It shows a Labelled Assigned Score (LAS) of 62.39, 4 points higher than the current best achieved for Tamil dependency parsing. Therefore, we show that breaking up the dependency parsing pipeline to accommodate existing tools and resources is a viable approach for low-resource languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sarveswaran-dias-2020-thamizhiudp">
<titleInfo>
<title>ThamizhiUDp: A Dependency Parser for Tamil</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kengatharaiyer</namePart>
<namePart type="family">Sarveswaran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gihan</namePart>
<namePart type="family">Dias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 17th International Conference on Natural Language Processing (ICON)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dipti</namePart>
<namePart type="given">Misra</namePart>
<namePart type="family">Sharma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rajeev</namePart>
<namePart type="family">Sangal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>NLP Association of India (NLPAI)</publisher>
<place>
<placeTerm type="text">Indian Institute of Technology Patna, Patna, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes how we developed a neural-based dependency parser, namely ThamizhiUDp, which provides a complete pipeline for the dependency parsing of the Tamil language text using Universal Dependency formalism. We have considered the phases of the dependency parsing pipeline and identified tools and resources in each of these phases to improve the accuracy and to tackle data scarcity. ThamizhiUDp uses Stanza for tokenisation and lemmatisation, ThamizhiPOSt and ThamizhiMorph for generating Part of Speech (POS) and Morphological annotations, and uuparser with multilingual training for dependency parsing. ThamizhiPOSt is our POS tagger, which is based on the Stanza, trained with Amrita POS-tagged corpus. It is the current state-of-the-art in Tamil POS tagging with an F1 score of 93.27. Our morphological analyzer, ThamizhiMorph is a rule-based system with a very good coverage of Tamil. Our dependency parser ThamizhiUDp was trained using multilingual data. It shows a Labelled Assigned Score (LAS) of 62.39, 4 points higher than the current best achieved for Tamil dependency parsing. Therefore, we show that breaking up the dependency parsing pipeline to accommodate existing tools and resources is a viable approach for low-resource languages.</abstract>
<identifier type="citekey">sarveswaran-dias-2020-thamizhiudp</identifier>
<location>
<url>https://aclanthology.org/2020.icon-main.26</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>200</start>
<end>207</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ThamizhiUDp: A Dependency Parser for Tamil
%A Sarveswaran, Kengatharaiyer
%A Dias, Gihan
%Y Bhattacharyya, Pushpak
%Y Sharma, Dipti Misra
%Y Sangal, Rajeev
%S Proceedings of the 17th International Conference on Natural Language Processing (ICON)
%D 2020
%8 December
%I NLP Association of India (NLPAI)
%C Indian Institute of Technology Patna, Patna, India
%F sarveswaran-dias-2020-thamizhiudp
%X This paper describes how we developed a neural-based dependency parser, namely ThamizhiUDp, which provides a complete pipeline for the dependency parsing of the Tamil language text using Universal Dependency formalism. We have considered the phases of the dependency parsing pipeline and identified tools and resources in each of these phases to improve the accuracy and to tackle data scarcity. ThamizhiUDp uses Stanza for tokenisation and lemmatisation, ThamizhiPOSt and ThamizhiMorph for generating Part of Speech (POS) and Morphological annotations, and uuparser with multilingual training for dependency parsing. ThamizhiPOSt is our POS tagger, which is based on the Stanza, trained with Amrita POS-tagged corpus. It is the current state-of-the-art in Tamil POS tagging with an F1 score of 93.27. Our morphological analyzer, ThamizhiMorph is a rule-based system with a very good coverage of Tamil. Our dependency parser ThamizhiUDp was trained using multilingual data. It shows a Labelled Assigned Score (LAS) of 62.39, 4 points higher than the current best achieved for Tamil dependency parsing. Therefore, we show that breaking up the dependency parsing pipeline to accommodate existing tools and resources is a viable approach for low-resource languages.
%U https://aclanthology.org/2020.icon-main.26
%P 200-207
Markdown (Informal)
[ThamizhiUDp: A Dependency Parser for Tamil](https://aclanthology.org/2020.icon-main.26) (Sarveswaran & Dias, ICON 2020)
ACL
- Kengatharaiyer Sarveswaran and Gihan Dias. 2020. ThamizhiUDp: A Dependency Parser for Tamil. In Proceedings of the 17th International Conference on Natural Language Processing (ICON), pages 200–207, Indian Institute of Technology Patna, Patna, India. NLP Association of India (NLPAI).