@inproceedings{cordova-2024-towards,
title = "Towards {U}niversal {D}ependencies for {A}ncash {Q}uechua",
author = "Cordova, Johanna",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.1450",
pages = "16680--16685",
abstract = "This paper presents a brief description of some morphosyntactic features of Ancash Quechua, the majority variety of the Central Quechua language family (QI), for the purpose of building a corpus annotated according to the Universal Dependencies (UD) schema. The creation of such a corpus has two objectives: for Quechua linguistics, it opens up the possibility of more systematic linguistic studies and comparisons with other languages. It also enables the development of a syntactic parser, which would be the first NLP tool for a Quechua language of this family. For the UD project, adding Quechua, an agglutinative language with a rich morphology, makes it possible to point out some possible shortcomings of the universal annotation schema, and to fuel the discussion to adapt this schema to the specific features of the languages with a similar typology. The first step towards this work was first to gather and digitise the available linguistic resources, thus creating the first bilingual and sentence-aligned digital corpus in Ancash Quechua and Spanish. After identifying some linguistic features not fully described in the UD schema, we proposed annotation solutions, and built an initial corpus of around twenty sentences, which we are making freely available.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cordova-2024-towards">
<titleInfo>
<title>Towards Universal Dependencies for Ancash Quechua</title>
</titleInfo>
<name type="personal">
<namePart type="given">Johanna</namePart>
<namePart type="family">Cordova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents a brief description of some morphosyntactic features of Ancash Quechua, the majority variety of the Central Quechua language family (QI), for the purpose of building a corpus annotated according to the Universal Dependencies (UD) schema. The creation of such a corpus has two objectives: for Quechua linguistics, it opens up the possibility of more systematic linguistic studies and comparisons with other languages. It also enables the development of a syntactic parser, which would be the first NLP tool for a Quechua language of this family. For the UD project, adding Quechua, an agglutinative language with a rich morphology, makes it possible to point out some possible shortcomings of the universal annotation schema, and to fuel the discussion to adapt this schema to the specific features of the languages with a similar typology. The first step towards this work was first to gather and digitise the available linguistic resources, thus creating the first bilingual and sentence-aligned digital corpus in Ancash Quechua and Spanish. After identifying some linguistic features not fully described in the UD schema, we proposed annotation solutions, and built an initial corpus of around twenty sentences, which we are making freely available.</abstract>
<identifier type="citekey">cordova-2024-towards</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1450</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>16680</start>
<end>16685</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards Universal Dependencies for Ancash Quechua
%A Cordova, Johanna
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F cordova-2024-towards
%X This paper presents a brief description of some morphosyntactic features of Ancash Quechua, the majority variety of the Central Quechua language family (QI), for the purpose of building a corpus annotated according to the Universal Dependencies (UD) schema. The creation of such a corpus has two objectives: for Quechua linguistics, it opens up the possibility of more systematic linguistic studies and comparisons with other languages. It also enables the development of a syntactic parser, which would be the first NLP tool for a Quechua language of this family. For the UD project, adding Quechua, an agglutinative language with a rich morphology, makes it possible to point out some possible shortcomings of the universal annotation schema, and to fuel the discussion to adapt this schema to the specific features of the languages with a similar typology. The first step towards this work was first to gather and digitise the available linguistic resources, thus creating the first bilingual and sentence-aligned digital corpus in Ancash Quechua and Spanish. After identifying some linguistic features not fully described in the UD schema, we proposed annotation solutions, and built an initial corpus of around twenty sentences, which we are making freely available.
%U https://aclanthology.org/2024.lrec-main.1450
%P 16680-16685
Markdown (Informal)
[Towards Universal Dependencies for Ancash Quechua](https://aclanthology.org/2024.lrec-main.1450) (Cordova, LREC-COLING 2024)
ACL
- Johanna Cordova. 2024. Towards Universal Dependencies for Ancash Quechua. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 16680–16685, Torino, Italia. ELRA and ICCL.