@inproceedings{adel-etal-2026-lost,
title = "Lost Between Scripts: Recovering {A}rabic Words from Noisy Learner Orthographies",
author = "Adel, Mohamed and
Shahid, Nisa and
Habash, Nizar",
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.1471/",
pages = "33661--33672",
ISBN = "979-8-89176-459-0",
abstract = "Recovering an intended word from a noisy spelling is a general word-retrieval problem relevant to language learning, spelling correction, and cross-script search. We study this problem in Arabic, where learners produce variable transcriptions in Arabic or Roman script that may preserve only part of the target form. Using ArabScribe, we evaluate four large language models (LLMs) on ranked intended-word recovery under three cue conditions: the noisy form, an English meaning gloss, and both. Combining form and meaning consistently outperforms either cue alone across models and scripts, with particularly strong benefits for distorted and Roman-script input. An expert-human evaluation shows the same benefit from glosses and places the strongest models near individual expert performance on the sampled items. Analyses of edit distance, learner proficiency, and target frequency show that semantic information improves recovery across difficulty conditions but does not eliminate sensitivity to form noise and lexical rarity. These findings establish gloss-grounded intended-word recovery as a useful framework for studying how LLMs integrate form and meaning under noisy, cross-script input."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="adel-etal-2026-lost">
<titleInfo>
<title>Lost Between Scripts: Recovering Arabic Words from Noisy Learner Orthographies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mohamed</namePart>
<namePart type="family">Adel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nisa</namePart>
<namePart type="family">Shahid</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nizar</namePart>
<namePart type="family">Habash</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>Recovering an intended word from a noisy spelling is a general word-retrieval problem relevant to language learning, spelling correction, and cross-script search. We study this problem in Arabic, where learners produce variable transcriptions in Arabic or Roman script that may preserve only part of the target form. Using ArabScribe, we evaluate four large language models (LLMs) on ranked intended-word recovery under three cue conditions: the noisy form, an English meaning gloss, and both. Combining form and meaning consistently outperforms either cue alone across models and scripts, with particularly strong benefits for distorted and Roman-script input. An expert-human evaluation shows the same benefit from glosses and places the strongest models near individual expert performance on the sampled items. Analyses of edit distance, learner proficiency, and target frequency show that semantic information improves recovery across difficulty conditions but does not eliminate sensitivity to form noise and lexical rarity. These findings establish gloss-grounded intended-word recovery as a useful framework for studying how LLMs integrate form and meaning under noisy, cross-script input.</abstract>
<identifier type="citekey">adel-etal-2026-lost</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.1471/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>33661</start>
<end>33672</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Lost Between Scripts: Recovering Arabic Words from Noisy Learner Orthographies
%A Adel, Mohamed
%A Shahid, Nisa
%A Habash, Nizar
%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 adel-etal-2026-lost
%X Recovering an intended word from a noisy spelling is a general word-retrieval problem relevant to language learning, spelling correction, and cross-script search. We study this problem in Arabic, where learners produce variable transcriptions in Arabic or Roman script that may preserve only part of the target form. Using ArabScribe, we evaluate four large language models (LLMs) on ranked intended-word recovery under three cue conditions: the noisy form, an English meaning gloss, and both. Combining form and meaning consistently outperforms either cue alone across models and scripts, with particularly strong benefits for distorted and Roman-script input. An expert-human evaluation shows the same benefit from glosses and places the strongest models near individual expert performance on the sampled items. Analyses of edit distance, learner proficiency, and target frequency show that semantic information improves recovery across difficulty conditions but does not eliminate sensitivity to form noise and lexical rarity. These findings establish gloss-grounded intended-word recovery as a useful framework for studying how LLMs integrate form and meaning under noisy, cross-script input.
%U https://aclanthology.org/2026.emnlp-main.1471/
%P 33661-33672
Markdown (Informal)
[Lost Between Scripts: Recovering Arabic Words from Noisy Learner Orthographies](https://aclanthology.org/2026.emnlp-main.1471/) (Adel et al., EMNLP 2026)
ACL