@inproceedings{faghiri-etal-2026-verifying,
title = "Verifying the Menzerath-Altmann law in the verbal domain in 180 languages",
author = "Faghiri, Pegah and
Gerdes, Kim and
Kahane, Sylvain",
editor = {{\c{C}}{\"o}ltekin, {\c{C}}a{\u{g}}r{\i} and
Dobrovoljc, Kaja},
booktitle = "Proceedings of the Ninth Workshop on {U}niversal {D}ependencies ({UDW} 2026)",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.udw-1.5/",
doi = "10.63317/34eabs2yfdfh",
pages = "76--90",
abstract = "We present a large-scale evaluation of the Menzerath-Altmann law (MAL) in the verbal domain across 180 languages, using the Universal Dependencies (UD) treebank collection (v2.17). MAL predicts that as the number of constituents of a linguistic unit increases, their average size decreases. We propose a robust metric to estimate the MAL effect across corpora of widely varying sizes and define threshold-based categories to classify languages along a MAL preference cline. Crucially, we analyse the preverbal and postverbal domains separately, in addition to the standard bilateral MAL, and control for potential sampling bias by comparing results across language families (Indo-European vs. non-Indo-European) and syntactic types (VO, OV and no dominant order). Our results confirm MAL as a typologically widespread preference but not an absolute universal: several languages display a trivial or even opposite (anti-MAL) tendency. Furthermore, we uncover a significant asymmetry between the two sides of the verb: the MAL effect is stronger in the postverbal domain, while anti-MAL is stronger in the preverbal domain. VO languages tend to show a stronger MAL preference postverbally, whereas OV languages do so preverbally. These findings challenge the widespread assumption that length-based ordering constraints apply symmetrically on both sides of the verb and contribute new cross-linguistic evidence to the debate on the interaction between dependency length minimization and constituent size."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="faghiri-etal-2026-verifying">
<titleInfo>
<title>Verifying the Menzerath-Altmann law in the verbal domain in 180 languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pegah</namePart>
<namePart type="family">Faghiri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kim</namePart>
<namePart type="family">Gerdes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sylvain</namePart>
<namePart type="family">Kahane</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 Ninth Workshop on Universal Dependencies (UDW 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Çağrı</namePart>
<namePart type="family">Çöltekin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kaja</namePart>
<namePart type="family">Dobrovoljc</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>We present a large-scale evaluation of the Menzerath-Altmann law (MAL) in the verbal domain across 180 languages, using the Universal Dependencies (UD) treebank collection (v2.17). MAL predicts that as the number of constituents of a linguistic unit increases, their average size decreases. We propose a robust metric to estimate the MAL effect across corpora of widely varying sizes and define threshold-based categories to classify languages along a MAL preference cline. Crucially, we analyse the preverbal and postverbal domains separately, in addition to the standard bilateral MAL, and control for potential sampling bias by comparing results across language families (Indo-European vs. non-Indo-European) and syntactic types (VO, OV and no dominant order). Our results confirm MAL as a typologically widespread preference but not an absolute universal: several languages display a trivial or even opposite (anti-MAL) tendency. Furthermore, we uncover a significant asymmetry between the two sides of the verb: the MAL effect is stronger in the postverbal domain, while anti-MAL is stronger in the preverbal domain. VO languages tend to show a stronger MAL preference postverbally, whereas OV languages do so preverbally. These findings challenge the widespread assumption that length-based ordering constraints apply symmetrically on both sides of the verb and contribute new cross-linguistic evidence to the debate on the interaction between dependency length minimization and constituent size.</abstract>
<identifier type="citekey">faghiri-etal-2026-verifying</identifier>
<identifier type="doi">10.63317/34eabs2yfdfh</identifier>
<location>
<url>https://aclanthology.org/2026.udw-1.5/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>76</start>
<end>90</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Verifying the Menzerath-Altmann law in the verbal domain in 180 languages
%A Faghiri, Pegah
%A Gerdes, Kim
%A Kahane, Sylvain
%Y Çöltekin, Çağrı
%Y Dobrovoljc, Kaja
%S Proceedings of the Ninth Workshop on Universal Dependencies (UDW 2026)
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma de Mallorca, Spain
%F faghiri-etal-2026-verifying
%X We present a large-scale evaluation of the Menzerath-Altmann law (MAL) in the verbal domain across 180 languages, using the Universal Dependencies (UD) treebank collection (v2.17). MAL predicts that as the number of constituents of a linguistic unit increases, their average size decreases. We propose a robust metric to estimate the MAL effect across corpora of widely varying sizes and define threshold-based categories to classify languages along a MAL preference cline. Crucially, we analyse the preverbal and postverbal domains separately, in addition to the standard bilateral MAL, and control for potential sampling bias by comparing results across language families (Indo-European vs. non-Indo-European) and syntactic types (VO, OV and no dominant order). Our results confirm MAL as a typologically widespread preference but not an absolute universal: several languages display a trivial or even opposite (anti-MAL) tendency. Furthermore, we uncover a significant asymmetry between the two sides of the verb: the MAL effect is stronger in the postverbal domain, while anti-MAL is stronger in the preverbal domain. VO languages tend to show a stronger MAL preference postverbally, whereas OV languages do so preverbally. These findings challenge the widespread assumption that length-based ordering constraints apply symmetrically on both sides of the verb and contribute new cross-linguistic evidence to the debate on the interaction between dependency length minimization and constituent size.
%R 10.63317/34eabs2yfdfh
%U https://aclanthology.org/2026.udw-1.5/
%U https://doi.org/10.63317/34eabs2yfdfh
%P 76-90
Markdown (Informal)
[Verifying the Menzerath-Altmann law in the verbal domain in 180 languages](https://aclanthology.org/2026.udw-1.5/) (Faghiri et al., UDW 2026)
ACL