@inproceedings{alhafni-etal-2026-bilingual,
title = "A Bilingual Bimodal Benchmark for {A}rabic-{E}nglish {NLP} across Grammatical Correction, Essay Scoring, Morphological Tagging, and Speech Recognition",
author = "Alhafni, Bashar and
Hamed, Injy and
Eryani, Fadhl and
Palfreyman, David and
Habash, Nizar",
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-1.137/",
doi = "10.63317/489vftd6umyh",
pages = "1732--1749",
abstract = "Building comprehensive datasets that support a variety of NLP tasks and cover a diversity of languages and domains is vital for NLP evaluation purposes. In this paper, we present ZAEBUC*, a dataset that builds upon and enriches prior corpora with new annotations and benchmarking experiments. ZAEBUC* serves as a benchmark for a range of NLP tasks, including grammatical error correction, automated essay scoring, automatic speech recognition, and morphological tagging, which includes tokenization, part-of-speech tagging, and lemmatization. The dataset covers Arabic and English in both written and spoken forms, offering a bilingual and bimodal resource. Furthermore, the corpus brings together a collection of resources gathered from a similar population, enabling cross-linguistic and cross-modal comparisons. We provide benchmarking results, demonstrating the performance of NLP models, including LLMs, across various tasks, languages, and modalities."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alhafni-etal-2026-bilingual">
<titleInfo>
<title>A Bilingual Bimodal Benchmark for Arabic-English NLP across Grammatical Correction, Essay Scoring, Morphological Tagging, and Speech Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bashar</namePart>
<namePart type="family">Alhafni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Injy</namePart>
<namePart type="family">Hamed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fadhl</namePart>
<namePart type="family">Eryani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Palfreyman</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>2026-05</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>Building comprehensive datasets that support a variety of NLP tasks and cover a diversity of languages and domains is vital for NLP evaluation purposes. In this paper, we present ZAEBUC*, a dataset that builds upon and enriches prior corpora with new annotations and benchmarking experiments. ZAEBUC* serves as a benchmark for a range of NLP tasks, including grammatical error correction, automated essay scoring, automatic speech recognition, and morphological tagging, which includes tokenization, part-of-speech tagging, and lemmatization. The dataset covers Arabic and English in both written and spoken forms, offering a bilingual and bimodal resource. Furthermore, the corpus brings together a collection of resources gathered from a similar population, enabling cross-linguistic and cross-modal comparisons. We provide benchmarking results, demonstrating the performance of NLP models, including LLMs, across various tasks, languages, and modalities.</abstract>
<identifier type="citekey">alhafni-etal-2026-bilingual</identifier>
<identifier type="doi">10.63317/489vftd6umyh</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.137/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>1732</start>
<end>1749</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Bilingual Bimodal Benchmark for Arabic-English NLP across Grammatical Correction, Essay Scoring, Morphological Tagging, and Speech Recognition
%A Alhafni, Bashar
%A Hamed, Injy
%A Eryani, Fadhl
%A Palfreyman, David
%A Habash, Nizar
%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 alhafni-etal-2026-bilingual
%X Building comprehensive datasets that support a variety of NLP tasks and cover a diversity of languages and domains is vital for NLP evaluation purposes. In this paper, we present ZAEBUC*, a dataset that builds upon and enriches prior corpora with new annotations and benchmarking experiments. ZAEBUC* serves as a benchmark for a range of NLP tasks, including grammatical error correction, automated essay scoring, automatic speech recognition, and morphological tagging, which includes tokenization, part-of-speech tagging, and lemmatization. The dataset covers Arabic and English in both written and spoken forms, offering a bilingual and bimodal resource. Furthermore, the corpus brings together a collection of resources gathered from a similar population, enabling cross-linguistic and cross-modal comparisons. We provide benchmarking results, demonstrating the performance of NLP models, including LLMs, across various tasks, languages, and modalities.
%R 10.63317/489vftd6umyh
%U https://aclanthology.org/2026.lrec-1.137/
%U https://doi.org/10.63317/489vftd6umyh
%P 1732-1749
Markdown (Informal)
[A Bilingual Bimodal Benchmark for Arabic-English NLP across Grammatical Correction, Essay Scoring, Morphological Tagging, and Speech Recognition](https://aclanthology.org/2026.lrec-1.137/) (Alhafni et al., LREC 2026)
ACL
- Bashar Alhafni, Injy Hamed, Fadhl Eryani, David Palfreyman, and Nizar Habash. 2026. A Bilingual Bimodal Benchmark for Arabic-English NLP across Grammatical Correction, Essay Scoring, Morphological Tagging, and Speech Recognition. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 1732–1749, Palma de Mallorca, Spain. ELRA Language Resource Association.