@inproceedings{park-etal-2021-expanding,
title = "Expanding {U}niversal {D}ependencies for Polysynthetic Languages: A Case of {S}t. {L}awrence {I}sland {Y}upik",
author = "Park, Hyunji Hayley and
Schwartz, Lane and
Tyers, Francis",
editor = "Mager, Manuel and
Oncevay, Arturo and
Rios, Annette and
Ruiz, Ivan Vladimir Meza and
Palmer, Alexis and
Neubig, Graham and
Kann, Katharina",
booktitle = "Proceedings of the First Workshop on Natural Language Processing for Indigenous Languages of the Americas",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.americasnlp-1.14/",
doi = "10.18653/v1/2021.americasnlp-1.14",
pages = "131--142",
abstract = "This paper describes the development of the first Universal Dependencies (UD) treebank for St. Lawrence Island Yupik, an endangered language spoken in the Bering Strait region. While the UD guidelines provided a general framework for our annotations, language-specific decisions were made necessary by the rich morphology of the polysynthetic language. Most notably, we annotated a corpus at the morpheme level as well as the word level. The morpheme level annotation was conducted using an existing morphological analyzer and manual disambiguation. By comparing the two resulting annotation schemes, we argue that morpheme-level annotation is essential for polysynthetic languages like St. Lawrence Island Yupik. Word-level annotation results in degenerate trees for some Yupik sentences and often fails to capture syntactic relations that can be manifested at the morpheme level. Dependency parsing experiments provide further support for morpheme-level annotation. Implications for UD annotation of other polysynthetic languages are discussed."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="park-etal-2021-expanding">
<titleInfo>
<title>Expanding Universal Dependencies for Polysynthetic Languages: A Case of St. Lawrence Island Yupik</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hyunji</namePart>
<namePart type="given">Hayley</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lane</namePart>
<namePart type="family">Schwartz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Tyers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Natural Language Processing for Indigenous Languages of the Americas</title>
</titleInfo>
<name type="personal">
<namePart type="given">Manuel</namePart>
<namePart type="family">Mager</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arturo</namePart>
<namePart type="family">Oncevay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Annette</namePart>
<namePart type="family">Rios</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="given">Vladimir</namePart>
<namePart type="given">Meza</namePart>
<namePart type="family">Ruiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexis</namePart>
<namePart type="family">Palmer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Graham</namePart>
<namePart type="family">Neubig</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katharina</namePart>
<namePart type="family">Kann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes the development of the first Universal Dependencies (UD) treebank for St. Lawrence Island Yupik, an endangered language spoken in the Bering Strait region. While the UD guidelines provided a general framework for our annotations, language-specific decisions were made necessary by the rich morphology of the polysynthetic language. Most notably, we annotated a corpus at the morpheme level as well as the word level. The morpheme level annotation was conducted using an existing morphological analyzer and manual disambiguation. By comparing the two resulting annotation schemes, we argue that morpheme-level annotation is essential for polysynthetic languages like St. Lawrence Island Yupik. Word-level annotation results in degenerate trees for some Yupik sentences and often fails to capture syntactic relations that can be manifested at the morpheme level. Dependency parsing experiments provide further support for morpheme-level annotation. Implications for UD annotation of other polysynthetic languages are discussed.</abstract>
<identifier type="citekey">park-etal-2021-expanding</identifier>
<identifier type="doi">10.18653/v1/2021.americasnlp-1.14</identifier>
<location>
<url>https://aclanthology.org/2021.americasnlp-1.14/</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>131</start>
<end>142</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Expanding Universal Dependencies for Polysynthetic Languages: A Case of St. Lawrence Island Yupik
%A Park, Hyunji Hayley
%A Schwartz, Lane
%A Tyers, Francis
%Y Mager, Manuel
%Y Oncevay, Arturo
%Y Rios, Annette
%Y Ruiz, Ivan Vladimir Meza
%Y Palmer, Alexis
%Y Neubig, Graham
%Y Kann, Katharina
%S Proceedings of the First Workshop on Natural Language Processing for Indigenous Languages of the Americas
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F park-etal-2021-expanding
%X This paper describes the development of the first Universal Dependencies (UD) treebank for St. Lawrence Island Yupik, an endangered language spoken in the Bering Strait region. While the UD guidelines provided a general framework for our annotations, language-specific decisions were made necessary by the rich morphology of the polysynthetic language. Most notably, we annotated a corpus at the morpheme level as well as the word level. The morpheme level annotation was conducted using an existing morphological analyzer and manual disambiguation. By comparing the two resulting annotation schemes, we argue that morpheme-level annotation is essential for polysynthetic languages like St. Lawrence Island Yupik. Word-level annotation results in degenerate trees for some Yupik sentences and often fails to capture syntactic relations that can be manifested at the morpheme level. Dependency parsing experiments provide further support for morpheme-level annotation. Implications for UD annotation of other polysynthetic languages are discussed.
%R 10.18653/v1/2021.americasnlp-1.14
%U https://aclanthology.org/2021.americasnlp-1.14/
%U https://doi.org/10.18653/v1/2021.americasnlp-1.14
%P 131-142
Markdown (Informal)
[Expanding Universal Dependencies for Polysynthetic Languages: A Case of St. Lawrence Island Yupik](https://aclanthology.org/2021.americasnlp-1.14/) (Park et al., AmericasNLP 2021)
ACL