@inproceedings{stevanak-suppa-2026-slovke,
title = "{S}lov{KE}: A Large-Scale Dataset and {LLM} Evaluation for {S}lovak Keyphrase Extraction",
author = "{\v{S}}teva{\v{n}}{\'a}k, D{\'a}vid and
Suppa, Marek",
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-1.283/",
doi = "10.63317/322dk2ztk5dj",
pages = "3534--3546",
abstract = "Keyphrase extraction for morphologically rich, low-resource languages remains understudied, largely due to the scarcity of suitable evaluation datasets. We address this gap for Slovak by constructing a dataset of 227,432 scientific abstracts with author-assigned keyphrases{---}scraped and systematically cleaned from the Slovak Central Register of Theses{---}representing a 25-fold increase over the largest prior Slovak resource and approaching the scale of established English benchmarks such as KP20K. Using this dataset, we benchmark three unsupervised baselines (YAKE, TextRank, KeyBERT with SlovakBERT embeddings) and evaluate KeyLLM, an LLM-based extraction method using GPT-3.5-turbo. Unsupervised baselines achieve at most 11.6{\%} exact-match $F1@6$, with a large gap to partial matching (up to 51.5{\%}), reflecting the difficulty of matching inflected surface forms to author-assigned keyphrases. KeyLLM narrows this exact{--}partial gap, producing keyphrases closer to the canonical forms assigned by authors, while manual evaluation on 100 documents ($\kappa = 0.61$) confirms that KeyLLM captures relevant concepts that automated exact matching underestimates. Our analysis identifies morphological mismatch as the dominant failure mode for statistical methods{---}a finding relevant to other inflected languages. The dataset (\url{https://huggingface.co/datasets/NaiveNeuron/SlovKE}) and evaluation code (\url{https://github.com/NaiveNeuron/SlovKE}) are publicly available."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="stevanak-suppa-2026-slovke">
<titleInfo>
<title>SlovKE: A Large-Scale Dataset and LLM Evaluation for Slovak Keyphrase Extraction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dávid</namePart>
<namePart type="family">Števaňák</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marek</namePart>
<namePart type="family">Suppa</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>Keyphrase extraction for morphologically rich, low-resource languages remains understudied, largely due to the scarcity of suitable evaluation datasets. We address this gap for Slovak by constructing a dataset of 227,432 scientific abstracts with author-assigned keyphrases—scraped and systematically cleaned from the Slovak Central Register of Theses—representing a 25-fold increase over the largest prior Slovak resource and approaching the scale of established English benchmarks such as KP20K. Using this dataset, we benchmark three unsupervised baselines (YAKE, TextRank, KeyBERT with SlovakBERT embeddings) and evaluate KeyLLM, an LLM-based extraction method using GPT-3.5-turbo. Unsupervised baselines achieve at most 11.6% exact-match F1@6, with a large gap to partial matching (up to 51.5%), reflecting the difficulty of matching inflected surface forms to author-assigned keyphrases. KeyLLM narrows this exact–partial gap, producing keyphrases closer to the canonical forms assigned by authors, while manual evaluation on 100 documents (ąppa = 0.61) confirms that KeyLLM captures relevant concepts that automated exact matching underestimates. Our analysis identifies morphological mismatch as the dominant failure mode for statistical methods—a finding relevant to other inflected languages. The dataset (https://huggingface.co/datasets/NaiveNeuron/SlovKE) and evaluation code (https://github.com/NaiveNeuron/SlovKE) are publicly available.</abstract>
<identifier type="citekey">stevanak-suppa-2026-slovke</identifier>
<identifier type="doi">10.63317/322dk2ztk5dj</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.283/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>3534</start>
<end>3546</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SlovKE: A Large-Scale Dataset and LLM Evaluation for Slovak Keyphrase Extraction
%A Števaňák, Dávid
%A Suppa, Marek
%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 stevanak-suppa-2026-slovke
%X Keyphrase extraction for morphologically rich, low-resource languages remains understudied, largely due to the scarcity of suitable evaluation datasets. We address this gap for Slovak by constructing a dataset of 227,432 scientific abstracts with author-assigned keyphrases—scraped and systematically cleaned from the Slovak Central Register of Theses—representing a 25-fold increase over the largest prior Slovak resource and approaching the scale of established English benchmarks such as KP20K. Using this dataset, we benchmark three unsupervised baselines (YAKE, TextRank, KeyBERT with SlovakBERT embeddings) and evaluate KeyLLM, an LLM-based extraction method using GPT-3.5-turbo. Unsupervised baselines achieve at most 11.6% exact-match F1@6, with a large gap to partial matching (up to 51.5%), reflecting the difficulty of matching inflected surface forms to author-assigned keyphrases. KeyLLM narrows this exact–partial gap, producing keyphrases closer to the canonical forms assigned by authors, while manual evaluation on 100 documents (ąppa = 0.61) confirms that KeyLLM captures relevant concepts that automated exact matching underestimates. Our analysis identifies morphological mismatch as the dominant failure mode for statistical methods—a finding relevant to other inflected languages. The dataset (https://huggingface.co/datasets/NaiveNeuron/SlovKE) and evaluation code (https://github.com/NaiveNeuron/SlovKE) are publicly available.
%R 10.63317/322dk2ztk5dj
%U https://aclanthology.org/2026.lrec-1.283/
%U https://doi.org/10.63317/322dk2ztk5dj
%P 3534-3546
Markdown (Informal)
[SlovKE: A Large-Scale Dataset and LLM Evaluation for Slovak Keyphrase Extraction](https://aclanthology.org/2026.lrec-1.283/) (Števaňák & Suppa, LREC 2026)
ACL