@inproceedings{fukasawa-2026-discovering,
title = "Discovering Hierarchical Semantic Structures in {EU} Regulatory Embeddings: A Comparison of Two K-means Solutions and Their Alignment with {E}uro{V}oc",
author = "Fukasawa, Kayoko",
editor = "Aletras, Nikolaos and
Chalkidis, Ilias and
Barrett, Leslie and
Goanț{\u{a}}, C{\u{a}}t{\u{a}}lina and
Preoțiuc-Pietro, Daniel and
Spanakis, Gerasimos and
Xu, Shanshan",
booktitle = "Proceedings of the Natural Legal Language Processing Workshop 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.nllp-1.34/",
pages = "382--398",
ISBN = "979-8-89176-494-1",
abstract = "EU regulations govern interconnected domains, yet the hierarchical organization and granularity of regulatory semantic structures remain insufficiently understood. We analyze 717 provisions from nine EU regulations, represented as 746 embedding units, using K-means and Ward linkage. Two independently optimized 80-cluster solutions reveal recurring domain specific and cross-regulatory themes but differ in hierarchical organization. Cross-solution analysis shows high centroid-level semantic correspondence (mean matched-centroid cosine similarity = 0.943) despite lower partition agreement (ARI = 0.520; mean membership Jaccard similarity = 0.492). We identify 10 split and nine merge candidates, suggesting potential local differences in semantic boundaries or granularity. Post-hoc EuroVoc alignment shows partial agreement with established categories and identifies two qualitative candidate branches spanning taxonomy boundaries. These findings suggest that broadly corresponding regulatory semantic structures can coexist with local differences in membership, hierarchy, and granularity."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fukasawa-2026-discovering">
<titleInfo>
<title>Discovering Hierarchical Semantic Structures in EU Regulatory Embeddings: A Comparison of Two K-means Solutions and Their Alignment with EuroVoc</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kayoko</namePart>
<namePart type="family">Fukasawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Natural Legal Language Processing Workshop 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nikolaos</namePart>
<namePart type="family">Aletras</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ilias</namePart>
<namePart type="family">Chalkidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leslie</namePart>
<namePart type="family">Barrett</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cătălina</namePart>
<namePart type="family">Goanță</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Preoțiuc-Pietro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gerasimos</namePart>
<namePart type="family">Spanakis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shanshan</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-494-1</identifier>
</relatedItem>
<abstract>EU regulations govern interconnected domains, yet the hierarchical organization and granularity of regulatory semantic structures remain insufficiently understood. We analyze 717 provisions from nine EU regulations, represented as 746 embedding units, using K-means and Ward linkage. Two independently optimized 80-cluster solutions reveal recurring domain specific and cross-regulatory themes but differ in hierarchical organization. Cross-solution analysis shows high centroid-level semantic correspondence (mean matched-centroid cosine similarity = 0.943) despite lower partition agreement (ARI = 0.520; mean membership Jaccard similarity = 0.492). We identify 10 split and nine merge candidates, suggesting potential local differences in semantic boundaries or granularity. Post-hoc EuroVoc alignment shows partial agreement with established categories and identifies two qualitative candidate branches spanning taxonomy boundaries. These findings suggest that broadly corresponding regulatory semantic structures can coexist with local differences in membership, hierarchy, and granularity.</abstract>
<identifier type="citekey">fukasawa-2026-discovering</identifier>
<location>
<url>https://aclanthology.org/2026.nllp-1.34/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>382</start>
<end>398</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Discovering Hierarchical Semantic Structures in EU Regulatory Embeddings: A Comparison of Two K-means Solutions and Their Alignment with EuroVoc
%A Fukasawa, Kayoko
%Y Aletras, Nikolaos
%Y Chalkidis, Ilias
%Y Barrett, Leslie
%Y Goanță, Cătălina
%Y Preoțiuc-Pietro, Daniel
%Y Spanakis, Gerasimos
%Y Xu, Shanshan
%S Proceedings of the Natural Legal Language Processing Workshop 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-494-1
%F fukasawa-2026-discovering
%X EU regulations govern interconnected domains, yet the hierarchical organization and granularity of regulatory semantic structures remain insufficiently understood. We analyze 717 provisions from nine EU regulations, represented as 746 embedding units, using K-means and Ward linkage. Two independently optimized 80-cluster solutions reveal recurring domain specific and cross-regulatory themes but differ in hierarchical organization. Cross-solution analysis shows high centroid-level semantic correspondence (mean matched-centroid cosine similarity = 0.943) despite lower partition agreement (ARI = 0.520; mean membership Jaccard similarity = 0.492). We identify 10 split and nine merge candidates, suggesting potential local differences in semantic boundaries or granularity. Post-hoc EuroVoc alignment shows partial agreement with established categories and identifies two qualitative candidate branches spanning taxonomy boundaries. These findings suggest that broadly corresponding regulatory semantic structures can coexist with local differences in membership, hierarchy, and granularity.
%U https://aclanthology.org/2026.nllp-1.34/
%P 382-398
Markdown (Informal)
[Discovering Hierarchical Semantic Structures in EU Regulatory Embeddings: A Comparison of Two K-means Solutions and Their Alignment with EuroVoc](https://aclanthology.org/2026.nllp-1.34/) (Fukasawa, NLLP 2026)
ACL