@inproceedings{olabe-bentz-2026-entropic,
title = "Entropic properties of languages in phonetic versus orthographic alphabets",
author = "Olabe, Carla and
Bentz, Christian",
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.92/",
pages = "2165--2183",
ISBN = "979-8-89176-459-0",
abstract = "Computational linguistics predominantly operates on written text. However, writing represents spoken language only indirectly. Whether phonetic and orthographic representations share fundamental information-theoretic properties is an open question. We present a cross-linguistic analysis of Shannon entropy across modalities using the DoReCo corpus featuring 42 languages of 25 families after preprocessing. By computing continuous entropy trajectories at orthographic word, subword (BPE), and character levels (UTF-8/SAMPA), we reveal a systematic modality convergence: orthographic and phonetic encodings yield consistently small entropy differences across all three granularity levels. This general pattern, however, masks notable cross-linguistic variation{--}some languages, such as Evenki, converge tightly across all levels, while others show modality gaps at specific granularities{--}for instance, English at the character level, Bora at the word level, and Sanzhi Dargwa at the subword level. In sum, Shannon entropy tends toward modality-invariance as a general tendency across the Latin-script languages examined, while leaving room for typologically conditioned divergence. Whether this pattern extends to non-alphabetic writing systems remains an open question."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="olabe-bentz-2026-entropic">
<titleInfo>
<title>Entropic properties of languages in phonetic versus orthographic alphabets</title>
</titleInfo>
<name type="personal">
<namePart type="given">Carla</namePart>
<namePart type="family">Olabe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christian</namePart>
<namePart type="family">Bentz</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>Computational linguistics predominantly operates on written text. However, writing represents spoken language only indirectly. Whether phonetic and orthographic representations share fundamental information-theoretic properties is an open question. We present a cross-linguistic analysis of Shannon entropy across modalities using the DoReCo corpus featuring 42 languages of 25 families after preprocessing. By computing continuous entropy trajectories at orthographic word, subword (BPE), and character levels (UTF-8/SAMPA), we reveal a systematic modality convergence: orthographic and phonetic encodings yield consistently small entropy differences across all three granularity levels. This general pattern, however, masks notable cross-linguistic variation–some languages, such as Evenki, converge tightly across all levels, while others show modality gaps at specific granularities–for instance, English at the character level, Bora at the word level, and Sanzhi Dargwa at the subword level. In sum, Shannon entropy tends toward modality-invariance as a general tendency across the Latin-script languages examined, while leaving room for typologically conditioned divergence. Whether this pattern extends to non-alphabetic writing systems remains an open question.</abstract>
<identifier type="citekey">olabe-bentz-2026-entropic</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.92/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>2165</start>
<end>2183</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Entropic properties of languages in phonetic versus orthographic alphabets
%A Olabe, Carla
%A Bentz, Christian
%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 olabe-bentz-2026-entropic
%X Computational linguistics predominantly operates on written text. However, writing represents spoken language only indirectly. Whether phonetic and orthographic representations share fundamental information-theoretic properties is an open question. We present a cross-linguistic analysis of Shannon entropy across modalities using the DoReCo corpus featuring 42 languages of 25 families after preprocessing. By computing continuous entropy trajectories at orthographic word, subword (BPE), and character levels (UTF-8/SAMPA), we reveal a systematic modality convergence: orthographic and phonetic encodings yield consistently small entropy differences across all three granularity levels. This general pattern, however, masks notable cross-linguistic variation–some languages, such as Evenki, converge tightly across all levels, while others show modality gaps at specific granularities–for instance, English at the character level, Bora at the word level, and Sanzhi Dargwa at the subword level. In sum, Shannon entropy tends toward modality-invariance as a general tendency across the Latin-script languages examined, while leaving room for typologically conditioned divergence. Whether this pattern extends to non-alphabetic writing systems remains an open question.
%U https://aclanthology.org/2026.emnlp-main.92/
%P 2165-2183
Markdown (Informal)
[Entropic properties of languages in phonetic versus orthographic alphabets](https://aclanthology.org/2026.emnlp-main.92/) (Olabe & Bentz, EMNLP 2026)
ACL