@inproceedings{sung-shin-2025-second,
title = "Second language {K}orean {U}niversal {D}ependency treebank v1.2: Focus on Data Augmentation and Annotation Scheme Refinement",
author = "Sung, Hakyung and
Shin, Gyu-Ho",
editor = "Holdt, {\v{S}}pela Arhar and
Ilinykh, Nikolai and
Scalvini, Barbara and
Bruton, Micaella and
Debess, Iben Nyholm and
Tudor, Crina Madalina",
booktitle = "Proceedings of the Third Workshop on Resources and Representations for Under-Resourced Languages and Domains (RESOURCEFUL-2025)",
month = mar,
year = "2025",
address = "Tallinn, Estonia",
publisher = "University of Tartu Library, Estonia",
url = "https://aclanthology.org/2025.resourceful-1.4/",
pages = "13--19",
ISBN = "978-9908-53-121-2",
abstract = "We expand the second language (L2) Korean Universal Dependencies (UD) treebank with 5,454 manually annotated sentences. The annotation guidelines are also revised to better align with the UD framework. Using this enhanced treebank, we fine-tune three Korean language models{---}Stanza, spaCy, and Trankit{---}and evaluate their performance on in-domain and out-of-domain L2-Korean datasets. The results show that fine-tuning significantly improves their performance across various metrics, thus highlighting the importance of using well-tailored L2 datasets for fine-tuning first-language-based, general-purpose language models for the morphosyntactic analysis of L2 data."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sung-shin-2025-second">
<titleInfo>
<title>Second language Korean Universal Dependency treebank v1.2: Focus on Data Augmentation and Annotation Scheme Refinement</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hakyung</namePart>
<namePart type="family">Sung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gyu-Ho</namePart>
<namePart type="family">Shin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Workshop on Resources and Representations for Under-Resourced Languages and Domains (RESOURCEFUL-2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Špela</namePart>
<namePart type="given">Arhar</namePart>
<namePart type="family">Holdt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikolai</namePart>
<namePart type="family">Ilinykh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="family">Scalvini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Micaella</namePart>
<namePart type="family">Bruton</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iben</namePart>
<namePart type="given">Nyholm</namePart>
<namePart type="family">Debess</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Crina</namePart>
<namePart type="given">Madalina</namePart>
<namePart type="family">Tudor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>University of Tartu Library, Estonia</publisher>
<place>
<placeTerm type="text">Tallinn, Estonia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">978-9908-53-121-2</identifier>
</relatedItem>
<abstract>We expand the second language (L2) Korean Universal Dependencies (UD) treebank with 5,454 manually annotated sentences. The annotation guidelines are also revised to better align with the UD framework. Using this enhanced treebank, we fine-tune three Korean language models—Stanza, spaCy, and Trankit—and evaluate their performance on in-domain and out-of-domain L2-Korean datasets. The results show that fine-tuning significantly improves their performance across various metrics, thus highlighting the importance of using well-tailored L2 datasets for fine-tuning first-language-based, general-purpose language models for the morphosyntactic analysis of L2 data.</abstract>
<identifier type="citekey">sung-shin-2025-second</identifier>
<location>
<url>https://aclanthology.org/2025.resourceful-1.4/</url>
</location>
<part>
<date>2025-03</date>
<extent unit="page">
<start>13</start>
<end>19</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Second language Korean Universal Dependency treebank v1.2: Focus on Data Augmentation and Annotation Scheme Refinement
%A Sung, Hakyung
%A Shin, Gyu-Ho
%Y Holdt, Špela Arhar
%Y Ilinykh, Nikolai
%Y Scalvini, Barbara
%Y Bruton, Micaella
%Y Debess, Iben Nyholm
%Y Tudor, Crina Madalina
%S Proceedings of the Third Workshop on Resources and Representations for Under-Resourced Languages and Domains (RESOURCEFUL-2025)
%D 2025
%8 March
%I University of Tartu Library, Estonia
%C Tallinn, Estonia
%@ 978-9908-53-121-2
%F sung-shin-2025-second
%X We expand the second language (L2) Korean Universal Dependencies (UD) treebank with 5,454 manually annotated sentences. The annotation guidelines are also revised to better align with the UD framework. Using this enhanced treebank, we fine-tune three Korean language models—Stanza, spaCy, and Trankit—and evaluate their performance on in-domain and out-of-domain L2-Korean datasets. The results show that fine-tuning significantly improves their performance across various metrics, thus highlighting the importance of using well-tailored L2 datasets for fine-tuning first-language-based, general-purpose language models for the morphosyntactic analysis of L2 data.
%U https://aclanthology.org/2025.resourceful-1.4/
%P 13-19
Markdown (Informal)
[Second language Korean Universal Dependency treebank v1.2: Focus on Data Augmentation and Annotation Scheme Refinement](https://aclanthology.org/2025.resourceful-1.4/) (Sung & Shin, RESOURCEFUL 2025)
ACL