@inproceedings{alghamdi-etal-2026-kashaf,
title = "{KASHAF}: A Hierarchical Resource and Pipeline for {A}rabic Interpretable Semantic Textual Similarity",
author = "AlGhamdi, Fahad and
Hawwari, Abdelati and
Alosaimy, Abdulrahman and
Almatham, Rawan Nasser and
Al Wazrah, Asma",
editor = "Abdul-Mageed, Muhammad and
Elsayed, Tamer and
Bouamor, Houda and
El-Beltagy, Samhaa and
Al-Khalifa, Hend and
Abdelali, Ahmed and
Elmadany, AbdelRahim and
El Mekki, Abdellah and
Darwish, Kareem and
Alkhereyf, Sakhar and
Luqman, Hamzah and
Khalifa, Salam and
Magdy, Samar and
Alyafeai, Zaid and
Hamed, Injy and
Zaghouani, Wajdi and
Zitouni, Imed",
booktitle = "Proceedings of The Fourth {A}rabic Natural Language Processing Conference",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.arabicnlp-main.31/",
pages = "444--461",
ISBN = "979-8-89176-473-6",
abstract = "We introduce KASHAF, to our knowledge the first interpretable Semantic Textual Similarity (iSTS) resource and end-to-end system for Arabic: a corpus of 7,811 human-annotated sentence pairs (inter-annotator {\ensuremath{\kappa}}=0.83{\ensuremath{\kappa}}= 0.83 {\ensuremath{\kappa}}=0.83 on a doubly-annotated subset) under a three-level hierarchical schema (sentence, phrase, and word), together with a modular pipeline that produces this layered analysis plus a composite similarity score, the KASHAF Hierarchical Similarity Score (KHSS), calibrated to the ordinal SEM scale. On a held-out cross-batch test split (1,002 pairs, disjoint from training and dev), KASHAF reaches macro-F1 =0.659= 0.659 =0.659 ({\ensuremath{\pm}}0.016{\ensuremath{\pm}}0.016 {\ensuremath{\pm}}0.016, 5 seeds) and Spearman {\ensuremath{\rho}}=0.6715{\ensuremath{\rho}}= 0.6715 {\ensuremath{\rho}}=0.6715; a rule-based antonym/negation polarity gate provides an empirical score-capping rule for high-similarity contradictions, and the MARBERTv2 backbone leads three alternative Arabic encoders. As an off-the-shelf diagnostic rather than a fine-tuned comparison, four contemporary LLMs under matched prompting reach at most macro-F1 0.215 (standard prompting) and 0.336 (chain-of-thought), a 32{--}44-point gap that reflects systematic over-prediction of SEM-PARA at the expense of the dominant SEM-PARTIAL class. We release the schema, guidelines, code, models, and a reproducibility pipeline; the corpus is available from KSAA on request."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alghamdi-etal-2026-kashaf">
<titleInfo>
<title>KASHAF: A Hierarchical Resource and Pipeline for Arabic Interpretable Semantic Textual Similarity</title>
</titleInfo>
<name type="personal">
<namePart type="given">Fahad</namePart>
<namePart type="family">AlGhamdi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdelati</namePart>
<namePart type="family">Hawwari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdulrahman</namePart>
<namePart type="family">Alosaimy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rawan</namePart>
<namePart type="given">Nasser</namePart>
<namePart type="family">Almatham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asma</namePart>
<namePart type="family">Al Wazrah</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 Fourth Arabic Natural Language Processing Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="family">Abdul-Mageed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tamer</namePart>
<namePart type="family">Elsayed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samhaa</namePart>
<namePart type="family">El-Beltagy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Abdelali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">AbdelRahim</namePart>
<namePart type="family">Elmadany</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdellah</namePart>
<namePart type="family">El Mekki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kareem</namePart>
<namePart type="family">Darwish</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakhar</namePart>
<namePart type="family">Alkhereyf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hamzah</namePart>
<namePart type="family">Luqman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Salam</namePart>
<namePart type="family">Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samar</namePart>
<namePart type="family">Magdy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zaid</namePart>
<namePart type="family">Alyafeai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Injy</namePart>
<namePart type="family">Hamed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wajdi</namePart>
<namePart type="family">Zaghouani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Imed</namePart>
<namePart type="family">Zitouni</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">979-8-89176-473-6</identifier>
</relatedItem>
<abstract>We introduce KASHAF, to our knowledge the first interpretable Semantic Textual Similarity (iSTS) resource and end-to-end system for Arabic: a corpus of 7,811 human-annotated sentence pairs (inter-annotator \ensuremathąppa=0.83\ensuremathąppa= 0.83 \ensuremathąppa=0.83 on a doubly-annotated subset) under a three-level hierarchical schema (sentence, phrase, and word), together with a modular pipeline that produces this layered analysis plus a composite similarity score, the KASHAF Hierarchical Similarity Score (KHSS), calibrated to the ordinal SEM scale. On a held-out cross-batch test split (1,002 pairs, disjoint from training and dev), KASHAF reaches macro-F1 =0.659= 0.659 =0.659 (\ensuremath\pm0.016\ensuremath\pm0.016 \ensuremath\pm0.016, 5 seeds) and Spearman \ensuremathρ=0.6715\ensuremathρ= 0.6715 \ensuremathρ=0.6715; a rule-based antonym/negation polarity gate provides an empirical score-capping rule for high-similarity contradictions, and the MARBERTv2 backbone leads three alternative Arabic encoders. As an off-the-shelf diagnostic rather than a fine-tuned comparison, four contemporary LLMs under matched prompting reach at most macro-F1 0.215 (standard prompting) and 0.336 (chain-of-thought), a 32–44-point gap that reflects systematic over-prediction of SEM-PARA at the expense of the dominant SEM-PARTIAL class. We release the schema, guidelines, code, models, and a reproducibility pipeline; the corpus is available from KSAA on request.</abstract>
<identifier type="citekey">alghamdi-etal-2026-kashaf</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-main.31/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>444</start>
<end>461</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T KASHAF: A Hierarchical Resource and Pipeline for Arabic Interpretable Semantic Textual Similarity
%A AlGhamdi, Fahad
%A Hawwari, Abdelati
%A Alosaimy, Abdulrahman
%A Almatham, Rawan Nasser
%A Al Wazrah, Asma
%Y Abdul-Mageed, Muhammad
%Y Elsayed, Tamer
%Y Bouamor, Houda
%Y El-Beltagy, Samhaa
%Y Al-Khalifa, Hend
%Y Abdelali, Ahmed
%Y Elmadany, AbdelRahim
%Y El Mekki, Abdellah
%Y Darwish, Kareem
%Y Alkhereyf, Sakhar
%Y Luqman, Hamzah
%Y Khalifa, Salam
%Y Magdy, Samar
%Y Alyafeai, Zaid
%Y Hamed, Injy
%Y Zaghouani, Wajdi
%Y Zitouni, Imed
%S Proceedings of The Fourth Arabic Natural Language Processing Conference
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-473-6
%F alghamdi-etal-2026-kashaf
%X We introduce KASHAF, to our knowledge the first interpretable Semantic Textual Similarity (iSTS) resource and end-to-end system for Arabic: a corpus of 7,811 human-annotated sentence pairs (inter-annotator \ensuremathąppa=0.83\ensuremathąppa= 0.83 \ensuremathąppa=0.83 on a doubly-annotated subset) under a three-level hierarchical schema (sentence, phrase, and word), together with a modular pipeline that produces this layered analysis plus a composite similarity score, the KASHAF Hierarchical Similarity Score (KHSS), calibrated to the ordinal SEM scale. On a held-out cross-batch test split (1,002 pairs, disjoint from training and dev), KASHAF reaches macro-F1 =0.659= 0.659 =0.659 (\ensuremath\pm0.016\ensuremath\pm0.016 \ensuremath\pm0.016, 5 seeds) and Spearman \ensuremathρ=0.6715\ensuremathρ= 0.6715 \ensuremathρ=0.6715; a rule-based antonym/negation polarity gate provides an empirical score-capping rule for high-similarity contradictions, and the MARBERTv2 backbone leads three alternative Arabic encoders. As an off-the-shelf diagnostic rather than a fine-tuned comparison, four contemporary LLMs under matched prompting reach at most macro-F1 0.215 (standard prompting) and 0.336 (chain-of-thought), a 32–44-point gap that reflects systematic over-prediction of SEM-PARA at the expense of the dominant SEM-PARTIAL class. We release the schema, guidelines, code, models, and a reproducibility pipeline; the corpus is available from KSAA on request.
%U https://aclanthology.org/2026.arabicnlp-main.31/
%P 444-461
Markdown (Informal)
[KASHAF: A Hierarchical Resource and Pipeline for Arabic Interpretable Semantic Textual Similarity](https://aclanthology.org/2026.arabicnlp-main.31/) (AlGhamdi et al., ArabicNLP 2026)
ACL