@inproceedings{elmadani-etal-2026-benchmark,
title = "A Benchmark for {A}rabic Lemma-Level Readability Assessment",
author = "Elmadani, Khalid N. and
Saeed, Mostafa and
Taha, Hanada 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.2314/",
pages = "52576--52599",
ISBN = "979-8-89176-459-0",
abstract = "We present BAREC-LexBench, a benchmark for Arabic lemma-level readability assessment, designed to evaluate readability lexicons and computational models independently of their granularity levels. We build the benchmark through a large-scale pairwise comparison task, where annotators determine which of two Arabic lemmas is easier to read and understand. The benchmark consists of 36,000 annotated pairs covering both same- and cross-part-of-speech comparisons among open-class lemmas: adjectives, nouns, proper nouns, and verbs. The annotations were produced by expert Arabic educators with an average inter-annotator agreement of 77.7{\%} (0.56 Kappa $\sim$ moderate agreement), and we analyze disagreement patterns to better understand where lemma-level readability judgments are most challenging. We benchmark a wide range of approaches, from readability lexicons and frequency-based lexicons to trainable models and large language models (LLMs). Finally, we demonstrate downstream uses of the benchmark by constructing a ranked readability lexicon covering open-class lemmas (BAREC-LexRank) and evaluating its contribution to sentence-level readability assessment. To support research and education, we make the dataset, ranked lexicon, and benchmark results openly available."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="elmadani-etal-2026-benchmark">
<titleInfo>
<title>A Benchmark for Arabic Lemma-Level Readability Assessment</title>
</titleInfo>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="given">N</namePart>
<namePart type="family">Elmadani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mostafa</namePart>
<namePart type="family">Saeed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hanada</namePart>
<namePart type="family">Taha</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>We present BAREC-LexBench, a benchmark for Arabic lemma-level readability assessment, designed to evaluate readability lexicons and computational models independently of their granularity levels. We build the benchmark through a large-scale pairwise comparison task, where annotators determine which of two Arabic lemmas is easier to read and understand. The benchmark consists of 36,000 annotated pairs covering both same- and cross-part-of-speech comparisons among open-class lemmas: adjectives, nouns, proper nouns, and verbs. The annotations were produced by expert Arabic educators with an average inter-annotator agreement of 77.7% (0.56 Kappa \sim moderate agreement), and we analyze disagreement patterns to better understand where lemma-level readability judgments are most challenging. We benchmark a wide range of approaches, from readability lexicons and frequency-based lexicons to trainable models and large language models (LLMs). Finally, we demonstrate downstream uses of the benchmark by constructing a ranked readability lexicon covering open-class lemmas (BAREC-LexRank) and evaluating its contribution to sentence-level readability assessment. To support research and education, we make the dataset, ranked lexicon, and benchmark results openly available.</abstract>
<identifier type="citekey">elmadani-etal-2026-benchmark</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.2314/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>52576</start>
<end>52599</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Benchmark for Arabic Lemma-Level Readability Assessment
%A Elmadani, Khalid N.
%A Saeed, Mostafa
%A Taha, Hanada
%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 elmadani-etal-2026-benchmark
%X We present BAREC-LexBench, a benchmark for Arabic lemma-level readability assessment, designed to evaluate readability lexicons and computational models independently of their granularity levels. We build the benchmark through a large-scale pairwise comparison task, where annotators determine which of two Arabic lemmas is easier to read and understand. The benchmark consists of 36,000 annotated pairs covering both same- and cross-part-of-speech comparisons among open-class lemmas: adjectives, nouns, proper nouns, and verbs. The annotations were produced by expert Arabic educators with an average inter-annotator agreement of 77.7% (0.56 Kappa \sim moderate agreement), and we analyze disagreement patterns to better understand where lemma-level readability judgments are most challenging. We benchmark a wide range of approaches, from readability lexicons and frequency-based lexicons to trainable models and large language models (LLMs). Finally, we demonstrate downstream uses of the benchmark by constructing a ranked readability lexicon covering open-class lemmas (BAREC-LexRank) and evaluating its contribution to sentence-level readability assessment. To support research and education, we make the dataset, ranked lexicon, and benchmark results openly available.
%U https://aclanthology.org/2026.emnlp-main.2314/
%P 52576-52599
Markdown (Informal)
[A Benchmark for Arabic Lemma-Level Readability Assessment](https://aclanthology.org/2026.emnlp-main.2314/) (Elmadani et al., EMNLP 2026)
ACL
- Khalid N. Elmadani, Mostafa Saeed, Hanada Taha, and Nizar Habash. 2026. A Benchmark for Arabic Lemma-Level Readability Assessment. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 52576–52599, Budapest, Hungary. Association for Computational Linguistics.