@inproceedings{diamantopoulos-sevcikova-2026-comparable,
title = "Comparable Corpora in Cross-linguistic Research: Nominal Number in {E}nglish, {C}zech, and {G}reek",
author = "Diamantopoulos, Konstantinos and
{\v{S}}ev{\v{c}}{\'i}kov{\'a}, Magda",
editor = "Rapp, Reinhard and
Terryn, Ayla Rigouts and
Sharoff, Serge and
Zweigenbaum, Pierre",
booktitle = "Proceedings of the 19th Workshop on Building and Using Comparable Corpora ({BUCC})",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.bucc-1.5/",
doi = "10.63317/4nz4cptoiwv3",
pages = "30--40",
abstract = "The paper examines the use of comparable corpora for contrastive research on the category of nominal number across three languages{---}English, Czech, and Greek. Two objectives are pursued: a cross-linguistic analysis of number and an assessment of the impact of automatic annotation on linguistic findings. For this study, corpora of comparable size and composition were compiled for the three languages from the Leipzig Corpora Collection. The data were automatically annotated using two open-access tools, Stanza and UDPipe, producing six datasets (two per language), each containing about 5 million sentences and 100 million tokens. Although derived from the same source, the paired datasets for each language differ in sentence and word segmentation, in the number of nouns identified, and in the number values assigned. These differences, nevertheless, do not appear to substantially affect the overall picture of number in the languages examined. The distribution of lemmas by the ratio of singular and plural forms challenges the view commonly presented in grammars that most nouns occur in both numbers and that singular-only and plural-only nouns are rare. However, a closer analysis of nouns assumed to have defective number indicates that answers to more nuanced questions vary depending on the annotation tool used."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="diamantopoulos-sevcikova-2026-comparable">
<titleInfo>
<title>Comparable Corpora in Cross-linguistic Research: Nominal Number in English, Czech, and Greek</title>
</titleInfo>
<name type="personal">
<namePart type="given">Konstantinos</namePart>
<namePart type="family">Diamantopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Magda</namePart>
<namePart type="family">Ševčíková</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 19th Workshop on Building and Using Comparable Corpora (BUCC)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Reinhard</namePart>
<namePart type="family">Rapp</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayla</namePart>
<namePart type="given">Rigouts</namePart>
<namePart type="family">Terryn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Serge</namePart>
<namePart type="family">Sharoff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pierre</namePart>
<namePart type="family">Zweigenbaum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The paper examines the use of comparable corpora for contrastive research on the category of nominal number across three languages—English, Czech, and Greek. Two objectives are pursued: a cross-linguistic analysis of number and an assessment of the impact of automatic annotation on linguistic findings. For this study, corpora of comparable size and composition were compiled for the three languages from the Leipzig Corpora Collection. The data were automatically annotated using two open-access tools, Stanza and UDPipe, producing six datasets (two per language), each containing about 5 million sentences and 100 million tokens. Although derived from the same source, the paired datasets for each language differ in sentence and word segmentation, in the number of nouns identified, and in the number values assigned. These differences, nevertheless, do not appear to substantially affect the overall picture of number in the languages examined. The distribution of lemmas by the ratio of singular and plural forms challenges the view commonly presented in grammars that most nouns occur in both numbers and that singular-only and plural-only nouns are rare. However, a closer analysis of nouns assumed to have defective number indicates that answers to more nuanced questions vary depending on the annotation tool used.</abstract>
<identifier type="citekey">diamantopoulos-sevcikova-2026-comparable</identifier>
<identifier type="doi">10.63317/4nz4cptoiwv3</identifier>
<location>
<url>https://aclanthology.org/2026.bucc-1.5/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>30</start>
<end>40</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Comparable Corpora in Cross-linguistic Research: Nominal Number in English, Czech, and Greek
%A Diamantopoulos, Konstantinos
%A Ševčíková, Magda
%Y Rapp, Reinhard
%Y Terryn, Ayla Rigouts
%Y Sharoff, Serge
%Y Zweigenbaum, Pierre
%S Proceedings of the 19th Workshop on Building and Using Comparable Corpora (BUCC)
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma de Mallorca, Spain
%F diamantopoulos-sevcikova-2026-comparable
%X The paper examines the use of comparable corpora for contrastive research on the category of nominal number across three languages—English, Czech, and Greek. Two objectives are pursued: a cross-linguistic analysis of number and an assessment of the impact of automatic annotation on linguistic findings. For this study, corpora of comparable size and composition were compiled for the three languages from the Leipzig Corpora Collection. The data were automatically annotated using two open-access tools, Stanza and UDPipe, producing six datasets (two per language), each containing about 5 million sentences and 100 million tokens. Although derived from the same source, the paired datasets for each language differ in sentence and word segmentation, in the number of nouns identified, and in the number values assigned. These differences, nevertheless, do not appear to substantially affect the overall picture of number in the languages examined. The distribution of lemmas by the ratio of singular and plural forms challenges the view commonly presented in grammars that most nouns occur in both numbers and that singular-only and plural-only nouns are rare. However, a closer analysis of nouns assumed to have defective number indicates that answers to more nuanced questions vary depending on the annotation tool used.
%R 10.63317/4nz4cptoiwv3
%U https://aclanthology.org/2026.bucc-1.5/
%U https://doi.org/10.63317/4nz4cptoiwv3
%P 30-40
Markdown (Informal)
[Comparable Corpora in Cross-linguistic Research: Nominal Number in English, Czech, and Greek](https://aclanthology.org/2026.bucc-1.5/) (Diamantopoulos & Ševčíková, BUCC 2026)
ACL