@inproceedings{kieras-etal-2026-corpus,
title = "The Corpus of Contemporary {P}olish {---} a New Reference Corpus with Rich Syntactic Annotations",
author = "Kiera{\'s}, Witold and
Marciniak, Ma{\l}gorzata and
Woli{\'n}ski, Marcin and
Krasnowska-Kiera{\'s}, Katarzyna and
{\L}azi{\'n}ski, 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-1.907/",
doi = "10.63317/2e37nxvjrs42",
pages = "11585--11592",
abstract = "In the paper, we describe the Corpus of Contemporary Polish (KWJP) and its rich syntactic annotation. The corpus covers a wide range of text originally published between 2011 and 2020. Although it carries on the idea of providing up-to-date reference corpora of Polish initiated by the National Corpus of Polish (NKJP) project, the principles underlying its development are not the same. In this article, we outline the different choices that affect corpora content and give an explanation for them. The article focuses mainly on the description of annotation layers in KWJP which are generated with a neural network based tool specially developed for this purpose. We describe in details syntactic structure annotation, which is represented by hybrid trees combining information typical to constituency and dependency trees. Finally, we provide several examples showing how annotation with hybrid trees facilitates querying and effective searching for information in the corpus."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kieras-etal-2026-corpus">
<titleInfo>
<title>The Corpus of Contemporary Polish — a New Reference Corpus with Rich Syntactic Annotations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Witold</namePart>
<namePart type="family">Kieraś</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Małgorzata</namePart>
<namePart type="family">Marciniak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcin</namePart>
<namePart type="family">Woliński</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katarzyna</namePart>
<namePart type="family">Krasnowska-Kieraś</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marek</namePart>
<namePart type="family">Łaziński</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>In the paper, we describe the Corpus of Contemporary Polish (KWJP) and its rich syntactic annotation. The corpus covers a wide range of text originally published between 2011 and 2020. Although it carries on the idea of providing up-to-date reference corpora of Polish initiated by the National Corpus of Polish (NKJP) project, the principles underlying its development are not the same. In this article, we outline the different choices that affect corpora content and give an explanation for them. The article focuses mainly on the description of annotation layers in KWJP which are generated with a neural network based tool specially developed for this purpose. We describe in details syntactic structure annotation, which is represented by hybrid trees combining information typical to constituency and dependency trees. Finally, we provide several examples showing how annotation with hybrid trees facilitates querying and effective searching for information in the corpus.</abstract>
<identifier type="citekey">kieras-etal-2026-corpus</identifier>
<identifier type="doi">10.63317/2e37nxvjrs42</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.907/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>11585</start>
<end>11592</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Corpus of Contemporary Polish — a New Reference Corpus with Rich Syntactic Annotations
%A Kieraś, Witold
%A Marciniak, Małgorzata
%A Woliński, Marcin
%A Krasnowska-Kieraś, Katarzyna
%A Łaziński, 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 kieras-etal-2026-corpus
%X In the paper, we describe the Corpus of Contemporary Polish (KWJP) and its rich syntactic annotation. The corpus covers a wide range of text originally published between 2011 and 2020. Although it carries on the idea of providing up-to-date reference corpora of Polish initiated by the National Corpus of Polish (NKJP) project, the principles underlying its development are not the same. In this article, we outline the different choices that affect corpora content and give an explanation for them. The article focuses mainly on the description of annotation layers in KWJP which are generated with a neural network based tool specially developed for this purpose. We describe in details syntactic structure annotation, which is represented by hybrid trees combining information typical to constituency and dependency trees. Finally, we provide several examples showing how annotation with hybrid trees facilitates querying and effective searching for information in the corpus.
%R 10.63317/2e37nxvjrs42
%U https://aclanthology.org/2026.lrec-1.907/
%U https://doi.org/10.63317/2e37nxvjrs42
%P 11585-11592
Markdown (Informal)
[The Corpus of Contemporary Polish — a New Reference Corpus with Rich Syntactic Annotations](https://aclanthology.org/2026.lrec-1.907/) (Kieraś et al., LREC 2026)
ACL