@inproceedings{badawy-etal-2026-bpe,
title = "{BPE} vs. Morphology-Aware Tokenization: A Case Study on {A}rabic Language Modeling at {B}aby{LM} Scale",
author = "Badawy, Mohamed and
Marco, Marion Di and
Fraser, Alexander",
editor = "Choshen, Leshem and
Cotterell, Ryan and
Gul, Mustafa Omer and
Jumelet, Jaap and
Linzen, Tal and
Mueller, Aaron and
Salhan, Suchir and
Shah, Raj Sanjay and
Warstadt, Alex and
Wilcox, Ethan Gotlieb",
booktitle = "Proceedings of the Second {B}aby{LM} Workshop",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.babylm-main.16/",
pages = "199--208",
ISBN = "979-8-89176-475-0",
abstract = "Byte Pair Encoding (BPE) is blind to morphology, a poor fit for Arabic, whose words bundle conjunctions, articles, and inflection into one token. The leading morphology-aware strategy for Arabic, MorphBPE, relies on Farasa, a supervised segmenter disallowed under the BabyLM 2026 rule against off-the-shelf linguistic tools. We study Arabic segmentation under the BabyLM GPT-2 training pipeline and propose Morfessor+MorphBPE, an unsupervised morphology-aware tokenizer.\par We compare two dimensions: supervised vs. unsupervised morphological segmentation and the merging constraints used by BPE. All tokenizer variants cluster within a narrow accuracy band, with improvements rather on language understanding tasks than knowledge tasks, even though we do not observe consistent improvements over BPE. Furthermore, we find that holding the Farasa segmentation fixed, the MorphBPE constraint sharply lowers perplexity but barely changes downstream accuracy; and unsupervised Morfessor boundaries match supervised Farasa on aggregate while scoring higher on grammaticality (MultiBLiMP). Morfessor+MorphBPE thus offers a practical path to morphology-aware tokenization for Arabic."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="badawy-etal-2026-bpe">
<titleInfo>
<title>BPE vs. Morphology-Aware Tokenization: A Case Study on Arabic Language Modeling at BabyLM Scale</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mohamed</namePart>
<namePart type="family">Badawy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marion</namePart>
<namePart type="given">Di</namePart>
<namePart type="family">Marco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Fraser</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 Second BabyLM Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Leshem</namePart>
<namePart type="family">Choshen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Cotterell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mustafa</namePart>
<namePart type="given">Omer</namePart>
<namePart type="family">Gul</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jaap</namePart>
<namePart type="family">Jumelet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tal</namePart>
<namePart type="family">Linzen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aaron</namePart>
<namePart type="family">Mueller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Suchir</namePart>
<namePart type="family">Salhan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raj</namePart>
<namePart type="given">Sanjay</namePart>
<namePart type="family">Shah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alex</namePart>
<namePart type="family">Warstadt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ethan</namePart>
<namePart type="given">Gotlieb</namePart>
<namePart type="family">Wilcox</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">979-8-89176-475-0</identifier>
</relatedItem>
<abstract>Byte Pair Encoding (BPE) is blind to morphology, a poor fit for Arabic, whose words bundle conjunctions, articles, and inflection into one token. The leading morphology-aware strategy for Arabic, MorphBPE, relies on Farasa, a supervised segmenter disallowed under the BabyLM 2026 rule against off-the-shelf linguistic tools. We study Arabic segmentation under the BabyLM GPT-2 training pipeline and propose Morfessor+MorphBPE, an unsupervised morphology-aware tokenizer.\par We compare two dimensions: supervised vs. unsupervised morphological segmentation and the merging constraints used by BPE. All tokenizer variants cluster within a narrow accuracy band, with improvements rather on language understanding tasks than knowledge tasks, even though we do not observe consistent improvements over BPE. Furthermore, we find that holding the Farasa segmentation fixed, the MorphBPE constraint sharply lowers perplexity but barely changes downstream accuracy; and unsupervised Morfessor boundaries match supervised Farasa on aggregate while scoring higher on grammaticality (MultiBLiMP). Morfessor+MorphBPE thus offers a practical path to morphology-aware tokenization for Arabic.</abstract>
<identifier type="citekey">badawy-etal-2026-bpe</identifier>
<location>
<url>https://aclanthology.org/2026.babylm-main.16/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>199</start>
<end>208</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BPE vs. Morphology-Aware Tokenization: A Case Study on Arabic Language Modeling at BabyLM Scale
%A Badawy, Mohamed
%A Marco, Marion Di
%A Fraser, Alexander
%Y Choshen, Leshem
%Y Cotterell, Ryan
%Y Gul, Mustafa Omer
%Y Jumelet, Jaap
%Y Linzen, Tal
%Y Mueller, Aaron
%Y Salhan, Suchir
%Y Shah, Raj Sanjay
%Y Warstadt, Alex
%Y Wilcox, Ethan Gotlieb
%S Proceedings of the Second BabyLM Workshop
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-475-0
%F badawy-etal-2026-bpe
%X Byte Pair Encoding (BPE) is blind to morphology, a poor fit for Arabic, whose words bundle conjunctions, articles, and inflection into one token. The leading morphology-aware strategy for Arabic, MorphBPE, relies on Farasa, a supervised segmenter disallowed under the BabyLM 2026 rule against off-the-shelf linguistic tools. We study Arabic segmentation under the BabyLM GPT-2 training pipeline and propose Morfessor+MorphBPE, an unsupervised morphology-aware tokenizer.\par We compare two dimensions: supervised vs. unsupervised morphological segmentation and the merging constraints used by BPE. All tokenizer variants cluster within a narrow accuracy band, with improvements rather on language understanding tasks than knowledge tasks, even though we do not observe consistent improvements over BPE. Furthermore, we find that holding the Farasa segmentation fixed, the MorphBPE constraint sharply lowers perplexity but barely changes downstream accuracy; and unsupervised Morfessor boundaries match supervised Farasa on aggregate while scoring higher on grammaticality (MultiBLiMP). Morfessor+MorphBPE thus offers a practical path to morphology-aware tokenization for Arabic.
%U https://aclanthology.org/2026.babylm-main.16/
%P 199-208
Markdown (Informal)
[BPE vs. Morphology-Aware Tokenization: A Case Study on Arabic Language Modeling at BabyLM Scale](https://aclanthology.org/2026.babylm-main.16/) (Badawy et al., BabyLM 2026)
ACL