@inproceedings{ku-etal-2026-structure,
title = "When Structure Matters: Cross-Lingual Hyperbolic Embeddings for {C}hinese and {E}nglish Wordnets",
author = "Ku, Mao-Chang and
Lian, Da-Chen and
Chen, Pin-Er and
Wang, Po-Ya Angela and
Chen, Wei-Ling and
HSIEH, Shu-Kai",
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-1.944/",
doi = "10.63317/55a4sr9mfucq",
pages = "12054--12071",
abstract = "Hyperbolic embeddings such as the Poincar{\'e} model effectively represent lexical hierarchies with low distortion, yet their cross-lingual generalizability remains largely unexplored. This study investigates cross-lingual transfer by training 20-dimensional Poincar{\'e} embeddings exclusively on Open English WordNet (OEWN) hypernymy relations and evaluating on aligned Chinese Wordnet (CWN) synsets under a vocabulary-constrained transfer setting, where CWN-relevant synsets appear in OEWN training data but no Chinese-language supervision is used. We report robust statistical evidence based on the final 10 training checkpoints: Poincar{\'e} embeddings achieve 2.57{\texttimes} higher Mean Reciprocal Rank (MRR) than Euclidean embeddings on CWN (0.030 {\ensuremath{\pm}} 0.001 vs 0.012 {\ensuremath{\pm}} 0.000, p {\ensuremath{<}} 0.001, Cohen{'}s d = 34.48) and 5.61{\texttimes} higher on OEWN (0.016 {\ensuremath{\pm}} 0.000 vs 0.003 {\ensuremath{\pm}} 0.000, p {\ensuremath{<}} 0.001, d = 42.48). Furthermore, hierarchical filtering leveraging the radial dimension of hyperbolic space provides substantial additional gains: +74.6{\%} MRR improvement on CWN and +25.8{\%} on OEWN (both p {\ensuremath{<}} 0.001). The model achieves higher absolute performance on the zero-shot CWN test set (MRR = 0.052 {\ensuremath{\pm}} 0.002) than on the in-domain OEWN test set (MRR = 0.020 {\ensuremath{\pm}} 0.001). We attribute this to structural alignment: CWN{'}s broader branching factor (4.32 vs 1.10) and moderate depth naturally suit hyperbolic geometry{'}s capacity to compactly represent hierarchies. Our findings demonstrate that geometric properties learned from English hypernymy transfer robustly across languages when semantic structures align. We release the aligned CWN{--}OEWN hypernymy evaluation dataset and complete evaluation framework to facilitate future research on geometry-based cross-lingual semantic modeling."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ku-etal-2026-structure">
<titleInfo>
<title>When Structure Matters: Cross-Lingual Hyperbolic Embeddings for Chinese and English Wordnets</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mao-Chang</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Da-Chen</namePart>
<namePart type="family">Lian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pin-Er</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Po-Ya</namePart>
<namePart type="given">Angela</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei-Ling</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shu-Kai</namePart>
<namePart type="family">HSIEH</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>Hyperbolic embeddings such as the Poincaré model effectively represent lexical hierarchies with low distortion, yet their cross-lingual generalizability remains largely unexplored. This study investigates cross-lingual transfer by training 20-dimensional Poincaré embeddings exclusively on Open English WordNet (OEWN) hypernymy relations and evaluating on aligned Chinese Wordnet (CWN) synsets under a vocabulary-constrained transfer setting, where CWN-relevant synsets appear in OEWN training data but no Chinese-language supervision is used. We report robust statistical evidence based on the final 10 training checkpoints: Poincaré embeddings achieve 2.57× higher Mean Reciprocal Rank (MRR) than Euclidean embeddings on CWN (0.030 \ensuremath\pm 0.001 vs 0.012 \ensuremath\pm 0.000, p \ensuremath< 0.001, Cohen’s d = 34.48) and 5.61× higher on OEWN (0.016 \ensuremath\pm 0.000 vs 0.003 \ensuremath\pm 0.000, p \ensuremath< 0.001, d = 42.48). Furthermore, hierarchical filtering leveraging the radial dimension of hyperbolic space provides substantial additional gains: +74.6% MRR improvement on CWN and +25.8% on OEWN (both p \ensuremath< 0.001). The model achieves higher absolute performance on the zero-shot CWN test set (MRR = 0.052 \ensuremath\pm 0.002) than on the in-domain OEWN test set (MRR = 0.020 \ensuremath\pm 0.001). We attribute this to structural alignment: CWN’s broader branching factor (4.32 vs 1.10) and moderate depth naturally suit hyperbolic geometry’s capacity to compactly represent hierarchies. Our findings demonstrate that geometric properties learned from English hypernymy transfer robustly across languages when semantic structures align. We release the aligned CWN–OEWN hypernymy evaluation dataset and complete evaluation framework to facilitate future research on geometry-based cross-lingual semantic modeling.</abstract>
<identifier type="citekey">ku-etal-2026-structure</identifier>
<identifier type="doi">10.63317/55a4sr9mfucq</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.944/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>12054</start>
<end>12071</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T When Structure Matters: Cross-Lingual Hyperbolic Embeddings for Chinese and English Wordnets
%A Ku, Mao-Chang
%A Lian, Da-Chen
%A Chen, Pin-Er
%A Wang, Po-Ya Angela
%A Chen, Wei-Ling
%A HSIEH, Shu-Kai
%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 ku-etal-2026-structure
%X Hyperbolic embeddings such as the Poincaré model effectively represent lexical hierarchies with low distortion, yet their cross-lingual generalizability remains largely unexplored. This study investigates cross-lingual transfer by training 20-dimensional Poincaré embeddings exclusively on Open English WordNet (OEWN) hypernymy relations and evaluating on aligned Chinese Wordnet (CWN) synsets under a vocabulary-constrained transfer setting, where CWN-relevant synsets appear in OEWN training data but no Chinese-language supervision is used. We report robust statistical evidence based on the final 10 training checkpoints: Poincaré embeddings achieve 2.57× higher Mean Reciprocal Rank (MRR) than Euclidean embeddings on CWN (0.030 \ensuremath\pm 0.001 vs 0.012 \ensuremath\pm 0.000, p \ensuremath< 0.001, Cohen’s d = 34.48) and 5.61× higher on OEWN (0.016 \ensuremath\pm 0.000 vs 0.003 \ensuremath\pm 0.000, p \ensuremath< 0.001, d = 42.48). Furthermore, hierarchical filtering leveraging the radial dimension of hyperbolic space provides substantial additional gains: +74.6% MRR improvement on CWN and +25.8% on OEWN (both p \ensuremath< 0.001). The model achieves higher absolute performance on the zero-shot CWN test set (MRR = 0.052 \ensuremath\pm 0.002) than on the in-domain OEWN test set (MRR = 0.020 \ensuremath\pm 0.001). We attribute this to structural alignment: CWN’s broader branching factor (4.32 vs 1.10) and moderate depth naturally suit hyperbolic geometry’s capacity to compactly represent hierarchies. Our findings demonstrate that geometric properties learned from English hypernymy transfer robustly across languages when semantic structures align. We release the aligned CWN–OEWN hypernymy evaluation dataset and complete evaluation framework to facilitate future research on geometry-based cross-lingual semantic modeling.
%R 10.63317/55a4sr9mfucq
%U https://aclanthology.org/2026.lrec-1.944/
%U https://doi.org/10.63317/55a4sr9mfucq
%P 12054-12071
Markdown (Informal)
[When Structure Matters: Cross-Lingual Hyperbolic Embeddings for Chinese and English Wordnets](https://aclanthology.org/2026.lrec-1.944/) (Ku et al., LREC 2026)
ACL