@inproceedings{pranjic-etal-2026-slovene,
title = "{S}lovene Morphological and Word Formation Segmentation: A Novel Dataset and Evaluation",
author = "Pranji{\'c}, Marko and
Kern, Boris and
Vor{\v{s}}i{\v{c}}, Ines and
Pollak, Senja",
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-1.140/",
doi = "10.63317/4f6rruft238c",
pages = "1781--1793",
abstract = "We introduce the first publicly available manually annotated dataset for morphological segmentation and word-formation analysis for Slovene, containing 1,935 words annotated by two domain experts. The dataset provides three types of linguistic information: morphological and word-formation segments with zero-morpheme and simplex annotations. We present a four-stage annotation approach achieving inter-annotator agreement of 86.80{\%} Krippendorff{'}s Alpha for morphological segmentation and 85.16{\%} for word-formation segments. Computational validation using a morphological segmentation model achieves 87.78{\%} BPR F1 on morphological segmentation and 83.05{\%} on word-formation segments. Despite being smaller than previous datasets derived from non-public esources, our dataset enables high performance and supports reproducible research for morphological analysis tools for Slovene."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pranjic-etal-2026-slovene">
<titleInfo>
<title>Slovene Morphological and Word Formation Segmentation: A Novel Dataset and Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marko</namePart>
<namePart type="family">Pranjić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Boris</namePart>
<namePart type="family">Kern</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ines</namePart>
<namePart type="family">Voršič</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Senja</namePart>
<namePart type="family">Pollak</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>We introduce the first publicly available manually annotated dataset for morphological segmentation and word-formation analysis for Slovene, containing 1,935 words annotated by two domain experts. The dataset provides three types of linguistic information: morphological and word-formation segments with zero-morpheme and simplex annotations. We present a four-stage annotation approach achieving inter-annotator agreement of 86.80% Krippendorff’s Alpha for morphological segmentation and 85.16% for word-formation segments. Computational validation using a morphological segmentation model achieves 87.78% BPR F1 on morphological segmentation and 83.05% on word-formation segments. Despite being smaller than previous datasets derived from non-public esources, our dataset enables high performance and supports reproducible research for morphological analysis tools for Slovene.</abstract>
<identifier type="citekey">pranjic-etal-2026-slovene</identifier>
<identifier type="doi">10.63317/4f6rruft238c</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.140/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>1781</start>
<end>1793</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Slovene Morphological and Word Formation Segmentation: A Novel Dataset and Evaluation
%A Pranjić, Marko
%A Kern, Boris
%A Voršič, Ines
%A Pollak, Senja
%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 pranjic-etal-2026-slovene
%X We introduce the first publicly available manually annotated dataset for morphological segmentation and word-formation analysis for Slovene, containing 1,935 words annotated by two domain experts. The dataset provides three types of linguistic information: morphological and word-formation segments with zero-morpheme and simplex annotations. We present a four-stage annotation approach achieving inter-annotator agreement of 86.80% Krippendorff’s Alpha for morphological segmentation and 85.16% for word-formation segments. Computational validation using a morphological segmentation model achieves 87.78% BPR F1 on morphological segmentation and 83.05% on word-formation segments. Despite being smaller than previous datasets derived from non-public esources, our dataset enables high performance and supports reproducible research for morphological analysis tools for Slovene.
%R 10.63317/4f6rruft238c
%U https://aclanthology.org/2026.lrec-1.140/
%U https://doi.org/10.63317/4f6rruft238c
%P 1781-1793
Markdown (Informal)
[Slovene Morphological and Word Formation Segmentation: A Novel Dataset and Evaluation](https://aclanthology.org/2026.lrec-1.140/) (Pranjić et al., LREC 2026)
ACL