@inproceedings{mus-etal-2025-creating,
title = "Creating a multi-layer Treebank for Tundra {N}enets",
author = "Mus, Nikolett and
Guillaume, Bruno and
Kahane, Sylvain and
Zeman, Daniel",
editor = {H{\"a}m{\"a}l{\"a}inen, Mika and
Rie{\ss}ler, Michael and
Morooka, Eiaki V. and
Kharlashkin, Lev},
booktitle = "Proceedings of the 10th International Workshop on Computational Linguistics for Uralic Languages",
month = dec,
year = "2025",
address = "Joensuu, Finland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.iwclul-1.11/",
pages = "77--86",
ISBN = "979-8-89176-360-9",
abstract = "This paper presents the development of the Tundra Nenets Universal Dependencies (UD) Treebank, the first syntactically annotated resource for the Samoyedic branch of the Uralic family. The treebank integrates spoken-language data and adopts the morphologically enhanced Surface-Syntactic UD (mSUD) framework to capture inflectional morphology and morphology-based syntactic relations. It further incorporates Information Structure annotation. The methodological workflow includes data selection, transcription conventions, sentence and lexeme segmentation, annotation of spoken-language features, lemmatization, treatment of morpheme status, part-of-speech and morphological tagging, and syntactic annotation based on the functional and distributional properties of syntactic elements. We also outline the principles guiding multi-level annotation and justify the theoretical choices underlying the integration of prosodic, morphological, and syntactic information."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mus-etal-2025-creating">
<titleInfo>
<title>Creating a multi-layer Treebank for Tundra Nenets</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nikolett</namePart>
<namePart type="family">Mus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bruno</namePart>
<namePart type="family">Guillaume</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sylvain</namePart>
<namePart type="family">Kahane</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>2025-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 10th International Workshop on Computational Linguistics for Uralic Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mika</namePart>
<namePart type="family">Hämäläinen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Rießler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eiaki</namePart>
<namePart type="given">V</namePart>
<namePart type="family">Morooka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lev</namePart>
<namePart type="family">Kharlashkin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Joensuu, Finland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-360-9</identifier>
</relatedItem>
<abstract>This paper presents the development of the Tundra Nenets Universal Dependencies (UD) Treebank, the first syntactically annotated resource for the Samoyedic branch of the Uralic family. The treebank integrates spoken-language data and adopts the morphologically enhanced Surface-Syntactic UD (mSUD) framework to capture inflectional morphology and morphology-based syntactic relations. It further incorporates Information Structure annotation. The methodological workflow includes data selection, transcription conventions, sentence and lexeme segmentation, annotation of spoken-language features, lemmatization, treatment of morpheme status, part-of-speech and morphological tagging, and syntactic annotation based on the functional and distributional properties of syntactic elements. We also outline the principles guiding multi-level annotation and justify the theoretical choices underlying the integration of prosodic, morphological, and syntactic information.</abstract>
<identifier type="citekey">mus-etal-2025-creating</identifier>
<location>
<url>https://aclanthology.org/2025.iwclul-1.11/</url>
</location>
<part>
<date>2025-12</date>
<extent unit="page">
<start>77</start>
<end>86</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Creating a multi-layer Treebank for Tundra Nenets
%A Mus, Nikolett
%A Guillaume, Bruno
%A Kahane, Sylvain
%A Zeman, Daniel
%Y Hämäläinen, Mika
%Y Rießler, Michael
%Y Morooka, Eiaki V.
%Y Kharlashkin, Lev
%S Proceedings of the 10th International Workshop on Computational Linguistics for Uralic Languages
%D 2025
%8 December
%I Association for Computational Linguistics
%C Joensuu, Finland
%@ 979-8-89176-360-9
%F mus-etal-2025-creating
%X This paper presents the development of the Tundra Nenets Universal Dependencies (UD) Treebank, the first syntactically annotated resource for the Samoyedic branch of the Uralic family. The treebank integrates spoken-language data and adopts the morphologically enhanced Surface-Syntactic UD (mSUD) framework to capture inflectional morphology and morphology-based syntactic relations. It further incorporates Information Structure annotation. The methodological workflow includes data selection, transcription conventions, sentence and lexeme segmentation, annotation of spoken-language features, lemmatization, treatment of morpheme status, part-of-speech and morphological tagging, and syntactic annotation based on the functional and distributional properties of syntactic elements. We also outline the principles guiding multi-level annotation and justify the theoretical choices underlying the integration of prosodic, morphological, and syntactic information.
%U https://aclanthology.org/2025.iwclul-1.11/
%P 77-86
Markdown (Informal)
[Creating a multi-layer Treebank for Tundra Nenets](https://aclanthology.org/2025.iwclul-1.11/) (Mus et al., IWCLUL 2025)
ACL
- Nikolett Mus, Bruno Guillaume, Sylvain Kahane, and Daniel Zeman. 2025. Creating a multi-layer Treebank for Tundra Nenets. In Proceedings of the 10th International Workshop on Computational Linguistics for Uralic Languages, pages 77–86, Joensuu, Finland. Association for Computational Linguistics.