@inproceedings{ohlidalova-2026-cross,
title = "Cross-Dataset Inconsistencies in Morphological Annotation: Evidence from {U}niversal {D}ependencies",
author = "Ohl{\'i}dalov{\'a}, Vlasta",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.917/",
doi = "10.63317/55hiti2bjus3",
pages = "11715--11723",
abstract = "Ensuring annotation consistency is a challenging task in language dataset development. While difficulty is typically increasing at higher levels of linguistic complexity, we show that it is a critical issue even for fundamental linguistic tasks such as morphological annotation. Contrary to previous research that targeted intra-dataset inconsistencies, this study investigates inconsistencies across various pre-existing datasets for the same language. On the example of Universal Dependencies datasets, we examined what morphological categories exhibit the most disagreement. The analysis revealed that there are specific categories with low inconsistency score that indicates good agreement on these features (namely Case, Gender, Number and to a lesser extent Animacy). On the other hand, the Part-of-Speech (UPOS) tag stands out as a ``red flag'' due to high inconsistency score. Analysis of the most frequent inconsistencies suggest that they are dataset-specific artifacts rather than inherently language-specific phenomena."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ohlidalova-2026-cross">
<titleInfo>
<title>Cross-Dataset Inconsistencies in Morphological Annotation: Evidence from Universal Dependencies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vlasta</namePart>
<namePart type="family">Ohlídalová</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Ensuring annotation consistency is a challenging task in language dataset development. While difficulty is typically increasing at higher levels of linguistic complexity, we show that it is a critical issue even for fundamental linguistic tasks such as morphological annotation. Contrary to previous research that targeted intra-dataset inconsistencies, this study investigates inconsistencies across various pre-existing datasets for the same language. On the example of Universal Dependencies datasets, we examined what morphological categories exhibit the most disagreement. The analysis revealed that there are specific categories with low inconsistency score that indicates good agreement on these features (namely Case, Gender, Number and to a lesser extent Animacy). On the other hand, the Part-of-Speech (UPOS) tag stands out as a “red flag” due to high inconsistency score. Analysis of the most frequent inconsistencies suggest that they are dataset-specific artifacts rather than inherently language-specific phenomena.</abstract>
<identifier type="citekey">ohlidalova-2026-cross</identifier>
<identifier type="doi">10.63317/55hiti2bjus3</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.917/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>11715</start>
<end>11723</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Cross-Dataset Inconsistencies in Morphological Annotation: Evidence from Universal Dependencies
%A Ohlídalová, Vlasta
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F ohlidalova-2026-cross
%X Ensuring annotation consistency is a challenging task in language dataset development. While difficulty is typically increasing at higher levels of linguistic complexity, we show that it is a critical issue even for fundamental linguistic tasks such as morphological annotation. Contrary to previous research that targeted intra-dataset inconsistencies, this study investigates inconsistencies across various pre-existing datasets for the same language. On the example of Universal Dependencies datasets, we examined what morphological categories exhibit the most disagreement. The analysis revealed that there are specific categories with low inconsistency score that indicates good agreement on these features (namely Case, Gender, Number and to a lesser extent Animacy). On the other hand, the Part-of-Speech (UPOS) tag stands out as a “red flag” due to high inconsistency score. Analysis of the most frequent inconsistencies suggest that they are dataset-specific artifacts rather than inherently language-specific phenomena.
%R 10.63317/55hiti2bjus3
%U https://aclanthology.org/2026.lrec-1.917/
%U https://doi.org/10.63317/55hiti2bjus3
%P 11715-11723
Markdown (Informal)
[Cross-Dataset Inconsistencies in Morphological Annotation: Evidence from Universal Dependencies](https://aclanthology.org/2026.lrec-1.917/) (Ohlídalová, LREC 2026)
ACL