@inproceedings{irastortza-urbieta-etal-2026-language,
title = "Language Mixture to Develop Accurate {G}alician Dependency Parsers: An Exploration of Its Effects",
author = "Irastortza-Urbieta, Xabier and
Garc{\'i}a-Miguel, Jos{\'e} M. and
Garcia, Marcos",
booktitle = "Proceedings of the 13th Workshop on {NLP} for Similar Languages, Varieties and Dialects",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.vardial-1.5/",
pages = "58--69",
abstract = "The development of accurate syntactic parsers remains a challenge for low-resource languages. To overcome it, the literature has proposed leveraging syntactic annotations from typologically related languages. This work investigates the viability and adequacy of this approach for Galician, evaluating the use of annotations from major Romance languages as source data. Our methodology extends beyond standard automatic evaluation to incorporate a detailed error analysis, which precisely quantifies the effects of multilingual training and assesses the practical scalability of the method. The results establish the necessity of embedding models for effective cross-lingual transfer and demonstrate that even languages not particularly close can yield adequate parsers. This work confirms the benefits of cross-lingual data augmentation while delineating its scalability limits. Furthermore, the error analysis identifies specific, typologically conditioned grammatical dependencies that remain persistent challenges for accurate dependency parsing."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="irastortza-urbieta-etal-2026-language">
<titleInfo>
<title>Language Mixture to Develop Accurate Galician Dependency Parsers: An Exploration of Its Effects</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xabier</namePart>
<namePart type="family">Irastortza-Urbieta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">José</namePart>
<namePart type="given">M</namePart>
<namePart type="family">García-Miguel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcos</namePart>
<namePart type="family">Garcia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 13th Workshop on NLP for Similar Languages, Varieties and Dialects</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The development of accurate syntactic parsers remains a challenge for low-resource languages. To overcome it, the literature has proposed leveraging syntactic annotations from typologically related languages. This work investigates the viability and adequacy of this approach for Galician, evaluating the use of annotations from major Romance languages as source data. Our methodology extends beyond standard automatic evaluation to incorporate a detailed error analysis, which precisely quantifies the effects of multilingual training and assesses the practical scalability of the method. The results establish the necessity of embedding models for effective cross-lingual transfer and demonstrate that even languages not particularly close can yield adequate parsers. This work confirms the benefits of cross-lingual data augmentation while delineating its scalability limits. Furthermore, the error analysis identifies specific, typologically conditioned grammatical dependencies that remain persistent challenges for accurate dependency parsing.</abstract>
<identifier type="citekey">irastortza-urbieta-etal-2026-language</identifier>
<location>
<url>https://aclanthology.org/2026.vardial-1.5/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>58</start>
<end>69</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Language Mixture to Develop Accurate Galician Dependency Parsers: An Exploration of Its Effects
%A Irastortza-Urbieta, Xabier
%A García-Miguel, José M.
%A Garcia, Marcos
%S Proceedings of the 13th Workshop on NLP for Similar Languages, Varieties and Dialects
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%F irastortza-urbieta-etal-2026-language
%X The development of accurate syntactic parsers remains a challenge for low-resource languages. To overcome it, the literature has proposed leveraging syntactic annotations from typologically related languages. This work investigates the viability and adequacy of this approach for Galician, evaluating the use of annotations from major Romance languages as source data. Our methodology extends beyond standard automatic evaluation to incorporate a detailed error analysis, which precisely quantifies the effects of multilingual training and assesses the practical scalability of the method. The results establish the necessity of embedding models for effective cross-lingual transfer and demonstrate that even languages not particularly close can yield adequate parsers. This work confirms the benefits of cross-lingual data augmentation while delineating its scalability limits. Furthermore, the error analysis identifies specific, typologically conditioned grammatical dependencies that remain persistent challenges for accurate dependency parsing.
%U https://aclanthology.org/2026.vardial-1.5/
%P 58-69
Markdown (Informal)
[Language Mixture to Develop Accurate Galician Dependency Parsers: An Exploration of Its Effects](https://aclanthology.org/2026.vardial-1.5/) (Irastortza-Urbieta et al., VarDial 2026)
ACL