@inproceedings{parida-etal-2022-universal,
title = "{U}niversal {D}ependency Treebank for {O}dia Language",
author = "Parida, Shantipriya and
Shabadi, Kalyanamalini and
Ojha, Atul Kr. and
Sahoo, Saraswati and
Dash, Satya Ranjan and
Dash, Bijayalaxmi",
editor = "Jha, Girish Nath and
L., Sobha and
Bali, Kalika and
Ojha, Atul Kr.",
booktitle = "Proceedings of the WILDRE-6 Workshop within the 13th Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.wildre-1.15",
pages = "84--89",
abstract = "This paper presents the first publicly available treebank of Odia, a morphologically rich low resource Indian language. The treebank contains approx. 1082 tokens (100 sentences) in Odia were selected from {``}Samantar{''}, the largest available parallel corpora collection for Indic languages. All the selected sentences are manually annotated following the {``}Universal Dependency{''} guidelines. The morphological analysis of the Odia treebank was performed using machine learning techniques. The Odia annotated treebank will enrich the Odia language resource and will help in building language technology tools for cross-lingual learning and typological research. We also build a preliminary Odia parser using a machine learning approach. The accuracy of the parser is 86.6{\%} Tokenization, 64.1{\%} UPOS, 63.78{\%} XPOS, 42.04{\%} UAS and 21.34{\%} LAS. Finally, the paper briefly discusses the linguistic analysis of the Odia UD treebank.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="parida-etal-2022-universal">
<titleInfo>
<title>Universal Dependency Treebank for Odia Language</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shantipriya</namePart>
<namePart type="family">Parida</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalyanamalini</namePart>
<namePart type="family">Shabadi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</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">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saraswati</namePart>
<namePart type="family">Sahoo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Satya</namePart>
<namePart type="given">Ranjan</namePart>
<namePart type="family">Dash</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bijayalaxmi</namePart>
<namePart type="family">Dash</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the WILDRE-6 Workshop within the 13th Language Resources and Evaluation Conference</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">Sobha</namePart>
<namePart type="family">L.</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">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</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents the first publicly available treebank of Odia, a morphologically rich low resource Indian language. The treebank contains approx. 1082 tokens (100 sentences) in Odia were selected from “Samantar”, the largest available parallel corpora collection for Indic languages. All the selected sentences are manually annotated following the “Universal Dependency” guidelines. The morphological analysis of the Odia treebank was performed using machine learning techniques. The Odia annotated treebank will enrich the Odia language resource and will help in building language technology tools for cross-lingual learning and typological research. We also build a preliminary Odia parser using a machine learning approach. The accuracy of the parser is 86.6% Tokenization, 64.1% UPOS, 63.78% XPOS, 42.04% UAS and 21.34% LAS. Finally, the paper briefly discusses the linguistic analysis of the Odia UD treebank.</abstract>
<identifier type="citekey">parida-etal-2022-universal</identifier>
<location>
<url>https://aclanthology.org/2022.wildre-1.15</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>84</start>
<end>89</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Universal Dependency Treebank for Odia Language
%A Parida, Shantipriya
%A Shabadi, Kalyanamalini
%A Ojha, Atul Kr.
%A Sahoo, Saraswati
%A Dash, Satya Ranjan
%A Dash, Bijayalaxmi
%Y Jha, Girish Nath
%Y L., Sobha
%Y Bali, Kalika
%Y Ojha, Atul Kr.
%S Proceedings of the WILDRE-6 Workshop within the 13th Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F parida-etal-2022-universal
%X This paper presents the first publicly available treebank of Odia, a morphologically rich low resource Indian language. The treebank contains approx. 1082 tokens (100 sentences) in Odia were selected from “Samantar”, the largest available parallel corpora collection for Indic languages. All the selected sentences are manually annotated following the “Universal Dependency” guidelines. The morphological analysis of the Odia treebank was performed using machine learning techniques. The Odia annotated treebank will enrich the Odia language resource and will help in building language technology tools for cross-lingual learning and typological research. We also build a preliminary Odia parser using a machine learning approach. The accuracy of the parser is 86.6% Tokenization, 64.1% UPOS, 63.78% XPOS, 42.04% UAS and 21.34% LAS. Finally, the paper briefly discusses the linguistic analysis of the Odia UD treebank.
%U https://aclanthology.org/2022.wildre-1.15
%P 84-89
Markdown (Informal)
[Universal Dependency Treebank for Odia Language](https://aclanthology.org/2022.wildre-1.15) (Parida et al., WILDRE 2022)
ACL
- Shantipriya Parida, Kalyanamalini Shabadi, Atul Kr. Ojha, Saraswati Sahoo, Satya Ranjan Dash, and Bijayalaxmi Dash. 2022. Universal Dependency Treebank for Odia Language. In Proceedings of the WILDRE-6 Workshop within the 13th Language Resources and Evaluation Conference, pages 84–89, Marseille, France. European Language Resources Association.