@inproceedings{monir-baou-2026-datashi,
title = "{DATASHI}: A Parallel {E}nglish{--}Tashlhiyt Corpus for Orthography Normalization and Low-Resource Language Processing.",
author = "Monir, Nasser-Eddine and
Baou, Zakaria",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.153/",
doi = "10.63317/2zekkx242a7h",
pages = "1947--1956",
abstract = "DATASHI is a new parallel English{--}Tashlhiyt corpus that fills a critical gap in computational resources for Amazigh languages. It contains 5,000 sentence pairs, including a 1,500-sentence subset with expert-standardized and non-standard user-generated versions, enabling systematic study of orthographic diversity and normalization. This dual design supports text-based NLP tasks{---}such as tokenization, translation, and normalization{---}and also serves as a foundation for read-speech data collection and multimodal alignment. Comprehensive evaluations with state-of-the-art Large Language Models (GPT-5, Claude Sonnet 4.5, Gemini 2.5 Pro, Mistral, Qwen3-Max) show clear improvements from zero-shot to few-shot prompting, with Gemini 2.5 Pro achieving the lowest word and character-level error rates and exhibiting robust cross-lingual generalization. A fine-grained analysis of edit operations{---}deletions, substitutions, and insertions{---}across phonological classes (geminates, emphatics, uvulars, and pharyngeals) further highlights model-specific sensitivities to marked Tashlhiyt features and provides new diagnostic insights for low-resource Amazigh orthography normalization."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="monir-baou-2026-datashi">
<titleInfo>
<title>DATASHI: A Parallel English–Tashlhiyt Corpus for Orthography Normalization and Low-Resource Language Processing.</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nasser-Eddine</namePart>
<namePart type="family">Monir</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zakaria</namePart>
<namePart type="family">Baou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>DATASHI is a new parallel English–Tashlhiyt corpus that fills a critical gap in computational resources for Amazigh languages. It contains 5,000 sentence pairs, including a 1,500-sentence subset with expert-standardized and non-standard user-generated versions, enabling systematic study of orthographic diversity and normalization. This dual design supports text-based NLP tasks—such as tokenization, translation, and normalization—and also serves as a foundation for read-speech data collection and multimodal alignment. Comprehensive evaluations with state-of-the-art Large Language Models (GPT-5, Claude Sonnet 4.5, Gemini 2.5 Pro, Mistral, Qwen3-Max) show clear improvements from zero-shot to few-shot prompting, with Gemini 2.5 Pro achieving the lowest word and character-level error rates and exhibiting robust cross-lingual generalization. A fine-grained analysis of edit operations—deletions, substitutions, and insertions—across phonological classes (geminates, emphatics, uvulars, and pharyngeals) further highlights model-specific sensitivities to marked Tashlhiyt features and provides new diagnostic insights for low-resource Amazigh orthography normalization.</abstract>
<identifier type="citekey">monir-baou-2026-datashi</identifier>
<identifier type="doi">10.63317/2zekkx242a7h</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.153/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>1947</start>
<end>1956</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DATASHI: A Parallel English–Tashlhiyt Corpus for Orthography Normalization and Low-Resource Language Processing.
%A Monir, Nasser-Eddine
%A Baou, Zakaria
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F monir-baou-2026-datashi
%X DATASHI is a new parallel English–Tashlhiyt corpus that fills a critical gap in computational resources for Amazigh languages. It contains 5,000 sentence pairs, including a 1,500-sentence subset with expert-standardized and non-standard user-generated versions, enabling systematic study of orthographic diversity and normalization. This dual design supports text-based NLP tasks—such as tokenization, translation, and normalization—and also serves as a foundation for read-speech data collection and multimodal alignment. Comprehensive evaluations with state-of-the-art Large Language Models (GPT-5, Claude Sonnet 4.5, Gemini 2.5 Pro, Mistral, Qwen3-Max) show clear improvements from zero-shot to few-shot prompting, with Gemini 2.5 Pro achieving the lowest word and character-level error rates and exhibiting robust cross-lingual generalization. A fine-grained analysis of edit operations—deletions, substitutions, and insertions—across phonological classes (geminates, emphatics, uvulars, and pharyngeals) further highlights model-specific sensitivities to marked Tashlhiyt features and provides new diagnostic insights for low-resource Amazigh orthography normalization.
%R 10.63317/2zekkx242a7h
%U https://aclanthology.org/2026.lrec-1.153/
%U https://doi.org/10.63317/2zekkx242a7h
%P 1947-1956
Markdown (Informal)
[DATASHI: A Parallel English–Tashlhiyt Corpus for Orthography Normalization and Low-Resource Language Processing.](https://aclanthology.org/2026.lrec-1.153/) (Monir & Baou, LREC 2026)
ACL