@inproceedings{sharma-etal-2026-size,
title = "Size Sound Symbolism Survives Genealogy Across 27 Languages",
author = "Sharma, Anika and
Wrenn, Emma and
Niu, Tianyi and
Srivastava, Shashank",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.1297/",
pages = "29520--29540",
ISBN = "979-8-89176-459-0",
abstract = "Sound symbolism, the non-arbitrary mapping between word sounds and meanings, is well known from effects like Bouba{--}Kiki. But its cross-linguistic scope is difficult to assess because phonological similarity can also arise from shared ancestry, contact, or language-specific inventories. We propose a genealogy-aware stress test for size sound symbolism across 27 languages spanning 13 language families, using 810 phonemically transcribed size adjectives validated with native-speaker audio. We treat cross-family iconicity as a hard generalization task: train on languages grouped by lexical distance to a held-out target, test transfer from increasingly distant languages, and apply adversarial pressure against similarity-bin and source-language cues. Interpretable bag-of-phoneme classifiers predict size above chance, with clear patterns involving /i/ for smallness and /o,a/ for largeness, while consonants add more language-specific cues. Adversarial training prevents the jointly trained model from exploiting genealogy while held-out size prediction stays above chance, though post-hoc probing shows language identity is still recoverable. The residual signal is small but consistent, indicating cross-family size cues."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sharma-etal-2026-size">
<titleInfo>
<title>Size Sound Symbolism Survives Genealogy Across 27 Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anika</namePart>
<namePart type="family">Sharma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emma</namePart>
<namePart type="family">Wrenn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tianyi</namePart>
<namePart type="family">Niu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shashank</namePart>
<namePart type="family">Srivastava</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 2026 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</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">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>Sound symbolism, the non-arbitrary mapping between word sounds and meanings, is well known from effects like Bouba–Kiki. But its cross-linguistic scope is difficult to assess because phonological similarity can also arise from shared ancestry, contact, or language-specific inventories. We propose a genealogy-aware stress test for size sound symbolism across 27 languages spanning 13 language families, using 810 phonemically transcribed size adjectives validated with native-speaker audio. We treat cross-family iconicity as a hard generalization task: train on languages grouped by lexical distance to a held-out target, test transfer from increasingly distant languages, and apply adversarial pressure against similarity-bin and source-language cues. Interpretable bag-of-phoneme classifiers predict size above chance, with clear patterns involving /i/ for smallness and /o,a/ for largeness, while consonants add more language-specific cues. Adversarial training prevents the jointly trained model from exploiting genealogy while held-out size prediction stays above chance, though post-hoc probing shows language identity is still recoverable. The residual signal is small but consistent, indicating cross-family size cues.</abstract>
<identifier type="citekey">sharma-etal-2026-size</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.1297/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>29520</start>
<end>29540</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Size Sound Symbolism Survives Genealogy Across 27 Languages
%A Sharma, Anika
%A Wrenn, Emma
%A Niu, Tianyi
%A Srivastava, Shashank
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F sharma-etal-2026-size
%X Sound symbolism, the non-arbitrary mapping between word sounds and meanings, is well known from effects like Bouba–Kiki. But its cross-linguistic scope is difficult to assess because phonological similarity can also arise from shared ancestry, contact, or language-specific inventories. We propose a genealogy-aware stress test for size sound symbolism across 27 languages spanning 13 language families, using 810 phonemically transcribed size adjectives validated with native-speaker audio. We treat cross-family iconicity as a hard generalization task: train on languages grouped by lexical distance to a held-out target, test transfer from increasingly distant languages, and apply adversarial pressure against similarity-bin and source-language cues. Interpretable bag-of-phoneme classifiers predict size above chance, with clear patterns involving /i/ for smallness and /o,a/ for largeness, while consonants add more language-specific cues. Adversarial training prevents the jointly trained model from exploiting genealogy while held-out size prediction stays above chance, though post-hoc probing shows language identity is still recoverable. The residual signal is small but consistent, indicating cross-family size cues.
%U https://aclanthology.org/2026.emnlp-main.1297/
%P 29520-29540
Markdown (Informal)
[Size Sound Symbolism Survives Genealogy Across 27 Languages](https://aclanthology.org/2026.emnlp-main.1297/) (Sharma et al., EMNLP 2026)
ACL
- Anika Sharma, Emma Wrenn, Tianyi Niu, and Shashank Srivastava. 2026. Size Sound Symbolism Survives Genealogy Across 27 Languages. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 29520–29540, Budapest, Hungary. Association for Computational Linguistics.