@inproceedings{ojha-zeman-2020-universal,
title = "{U}niversal {D}ependency Treebanks for Low-Resource {I}ndian Languages: The Case of {B}hojpuri",
author = "Ojha, Atul Kr. and
Zeman, Daniel",
editor = "Jha, Girish Nath and
Bali, Kalika and
L., Sobha and
Agrawal, S. S. and
Ojha, Atul Kr.",
booktitle = "Proceedings of the WILDRE5{--} 5th Workshop on Indian Language Data: Resources and Evaluation",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/2020.wildre-1.7",
pages = "33--38",
abstract = "This paper presents the first dependency treebank for Bhojpuri, a resource-poor language that belongs to the Indo-Aryan language family. The objective behind the Bhojpuri Treebank (BHTB) project is to create a substantial, syntactically annotated treebank which not only acts as a valuable resource in building language technological tools, also helps in cross-lingual learning and typological research. Currently, the treebank consists of 4,881 annotated tokens in accordance with the annotation scheme of Universal Dependencies (UD). A Bhojpuri tagger and parser were created using machine learning approach. The accuracy of the model is 57.49{\%} UAS, 45.50{\%} LAS, 79.69{\%} UPOS accuracy and 77.64{\%} XPOS accuracy. The paper describes the details of the project including a discussion on linguistic analysis and annotation process of the Bhojpuri UD treebank.",
language = "English",
ISBN = "979-10-95546-67-2",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ojha-zeman-2020-universal">
<titleInfo>
<title>Universal Dependency Treebanks for Low-Resource Indian Languages: The Case of Bhojpuri</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Zeman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the WILDRE5– 5th Workshop on Indian Language Data: Resources and Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Girish</namePart>
<namePart type="given">Nath</namePart>
<namePart type="family">Jha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sobha</namePart>
<namePart type="family">L.</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">S</namePart>
<namePart type="given">S</namePart>
<namePart type="family">Agrawal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-67-2</identifier>
</relatedItem>
<abstract>This paper presents the first dependency treebank for Bhojpuri, a resource-poor language that belongs to the Indo-Aryan language family. The objective behind the Bhojpuri Treebank (BHTB) project is to create a substantial, syntactically annotated treebank which not only acts as a valuable resource in building language technological tools, also helps in cross-lingual learning and typological research. Currently, the treebank consists of 4,881 annotated tokens in accordance with the annotation scheme of Universal Dependencies (UD). A Bhojpuri tagger and parser were created using machine learning approach. The accuracy of the model is 57.49% UAS, 45.50% LAS, 79.69% UPOS accuracy and 77.64% XPOS accuracy. The paper describes the details of the project including a discussion on linguistic analysis and annotation process of the Bhojpuri UD treebank.</abstract>
<identifier type="citekey">ojha-zeman-2020-universal</identifier>
<location>
<url>https://aclanthology.org/2020.wildre-1.7</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>33</start>
<end>38</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Universal Dependency Treebanks for Low-Resource Indian Languages: The Case of Bhojpuri
%A Ojha, Atul Kr.
%A Zeman, Daniel
%Y Jha, Girish Nath
%Y Bali, Kalika
%Y L., Sobha
%Y Agrawal, S. S.
%Y Ojha, Atul Kr.
%S Proceedings of the WILDRE5– 5th Workshop on Indian Language Data: Resources and Evaluation
%D 2020
%8 May
%I European Language Resources Association (ELRA)
%C Marseille, France
%@ 979-10-95546-67-2
%G English
%F ojha-zeman-2020-universal
%X This paper presents the first dependency treebank for Bhojpuri, a resource-poor language that belongs to the Indo-Aryan language family. The objective behind the Bhojpuri Treebank (BHTB) project is to create a substantial, syntactically annotated treebank which not only acts as a valuable resource in building language technological tools, also helps in cross-lingual learning and typological research. Currently, the treebank consists of 4,881 annotated tokens in accordance with the annotation scheme of Universal Dependencies (UD). A Bhojpuri tagger and parser were created using machine learning approach. The accuracy of the model is 57.49% UAS, 45.50% LAS, 79.69% UPOS accuracy and 77.64% XPOS accuracy. The paper describes the details of the project including a discussion on linguistic analysis and annotation process of the Bhojpuri UD treebank.
%U https://aclanthology.org/2020.wildre-1.7
%P 33-38
Markdown (Informal)
[Universal Dependency Treebanks for Low-Resource Indian Languages: The Case of Bhojpuri](https://aclanthology.org/2020.wildre-1.7) (Ojha & Zeman, WILDRE 2020)
ACL