@inproceedings{vico-libovicky-2026-talk,
title = "What Do We Talk About When We Talk About Tokenization?",
author = "Vico, Gianluca and
Libovick{\'y}, Jind{\v{r}}ich",
editor = "Adelani, David Ifeoluwa and
Alabi, Jesujoba and
Arnett, Catherine and
Chang, Tyler and
Downey, C.M. and
Goldman, Omer and
Li, Senyu and
Miranda, Lester James Validad and
Qi, Jirui and
Stap, David and
Winata, Genta Indra and
Zhang, Xinyu Crystina",
booktitle = "Proceedings of the 6th Workshop on Multilingual Representation Learning ({MRL} 2026)",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.mrl-1.26/",
pages = "320--333",
ISBN = "979-8-89176-469-9",
abstract = "Tokenization appears across a large and heterogeneous body of NLP literature, most often as a design choice rather than the primary focus. We identify more than 800 such papers published over the last decade and use an LLM-based methodology to survey them at a scale that would not be feasible through manual review. We analyze four dimensions: the languages studied, the evaluation tasks, the intrinsic metrics used, and the granularity of the tokenization units considered. We find that machine translation is the most frequently studied topic when tokenization is discussed. Despite the multilingual focus of much of this work, a strong English and Eurocentric bias persists. Subword tokenization dominates in practice despite sustained research interest in characters, bytes, and morphemes. We release the extracted dataset to support further analysis."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vico-libovicky-2026-talk">
<titleInfo>
<title>What Do We Talk About When We Talk About Tokenization?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gianluca</namePart>
<namePart type="family">Vico</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jindřich</namePart>
<namePart type="family">Libovický</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 6th Workshop on Multilingual Representation Learning (MRL 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="given">Ifeoluwa</namePart>
<namePart type="family">Adelani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jesujoba</namePart>
<namePart type="family">Alabi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Catherine</namePart>
<namePart type="family">Arnett</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tyler</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">C</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Downey</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Omer</namePart>
<namePart type="family">Goldman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Senyu</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lester</namePart>
<namePart type="given">James</namePart>
<namePart type="given">Validad</namePart>
<namePart type="family">Miranda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jirui</namePart>
<namePart type="family">Qi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Stap</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Genta</namePart>
<namePart type="given">Indra</namePart>
<namePart type="family">Winata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinyu</namePart>
<namePart type="given">Crystina</namePart>
<namePart type="family">Zhang</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">979-8-89176-469-9</identifier>
</relatedItem>
<abstract>Tokenization appears across a large and heterogeneous body of NLP literature, most often as a design choice rather than the primary focus. We identify more than 800 such papers published over the last decade and use an LLM-based methodology to survey them at a scale that would not be feasible through manual review. We analyze four dimensions: the languages studied, the evaluation tasks, the intrinsic metrics used, and the granularity of the tokenization units considered. We find that machine translation is the most frequently studied topic when tokenization is discussed. Despite the multilingual focus of much of this work, a strong English and Eurocentric bias persists. Subword tokenization dominates in practice despite sustained research interest in characters, bytes, and morphemes. We release the extracted dataset to support further analysis.</abstract>
<identifier type="citekey">vico-libovicky-2026-talk</identifier>
<location>
<url>https://aclanthology.org/2026.mrl-1.26/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>320</start>
<end>333</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T What Do We Talk About When We Talk About Tokenization?
%A Vico, Gianluca
%A Libovický, Jindřich
%Y Adelani, David Ifeoluwa
%Y Alabi, Jesujoba
%Y Arnett, Catherine
%Y Chang, Tyler
%Y Downey, C. M.
%Y Goldman, Omer
%Y Li, Senyu
%Y Miranda, Lester James Validad
%Y Qi, Jirui
%Y Stap, David
%Y Winata, Genta Indra
%Y Zhang, Xinyu Crystina
%S Proceedings of the 6th Workshop on Multilingual Representation Learning (MRL 2026)
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-469-9
%F vico-libovicky-2026-talk
%X Tokenization appears across a large and heterogeneous body of NLP literature, most often as a design choice rather than the primary focus. We identify more than 800 such papers published over the last decade and use an LLM-based methodology to survey them at a scale that would not be feasible through manual review. We analyze four dimensions: the languages studied, the evaluation tasks, the intrinsic metrics used, and the granularity of the tokenization units considered. We find that machine translation is the most frequently studied topic when tokenization is discussed. Despite the multilingual focus of much of this work, a strong English and Eurocentric bias persists. Subword tokenization dominates in practice despite sustained research interest in characters, bytes, and morphemes. We release the extracted dataset to support further analysis.
%U https://aclanthology.org/2026.mrl-1.26/
%P 320-333
Markdown (Informal)
[What Do We Talk About When We Talk About Tokenization?](https://aclanthology.org/2026.mrl-1.26/) (Vico & Libovický, MRL 2026)
ACL