Mustafa Jarrar

Mustafa Jarrar, Fadi A Zaraket, Tymaa Hammouda et al.

This article presents morphologically-annotated Yemeni, Sudanese, Iraqi, and Libyan Arabic dialects Lisan corpora. Lisan features around 1.2 million tokens. We collected the content of the corpora from several social media platforms. The Yemeni corpus (~ 1.05M tokens) was collected automatically from Twitter. The corpora of the other three dialects (~ 50K tokens each) came manually from Facebook and YouTube posts and comments. Thirty five (35) annotators who are native speakers of the target dialects carried out the annotations. The annotators segemented all words in the four corpora into prefixes, stems and suffixes and labeled each with different morphological features such as part of speech, lemma, and a gloss in English. An Arabic Dialect Annotation Toolkit ADAT was developped for the purpose of the annation. The annotators were trained on a set of guidelines and on how to use ADAT. We developed ADAT to assist the annotators and to ensure compatibility with SAMA and Curras tagsets. The tool is open source, and the four corpora are also available online.

Mustafa Jarrar, Sanad Malaysha, Tymaa Hammouda et al.

SALMA, the first Arabic sense-annotated corpus, consists of ~34K tokens, which are all sense-annotated. The corpus is annotated using two different sense inventories simultaneously (Modern and Ghani). SALMA novelty lies in how tokens and senses are associated. Instead of linking a token to only one intended sense, SALMA links a token to multiple senses and provides a score to each sense. A smart web-based annotation tool was developed to support scoring multiple senses against a given word. In addition to sense annotations, we also annotated the corpus using six types of named entities. The quality of our annotations was assessed using various metrics (Kappa, Linear Weighted Kappa, Quadratic Weighted Kappa, Mean Average Error, and Root Mean Square Error), which show very high inter-annotator agreement. To establish a Word Sense Disambiguation baseline using our SALMA corpus, we developed an end-to-end Word Sense Disambiguation system using Target Sense Verification. We used this system to evaluate three Target Sense Verification models available in the literature. Our best model achieved an accuracy with 84.2% using Modern and 78.7% using Ghani. The full corpus and the annotation tool are open-source and publicly available at https://sina.birzeit.edu/salma/.

Haneen Liqreina, Mustafa Jarrar, Mohammed Khalilia et al.

Traditional NER systems are typically trained to recognize coarse-grained entities, and less attention is given to classifying entities into a hierarchy of fine-grained lower-level subtypes. This article aims to advance Arabic NER with fine-grained entities. We chose to extend Wojood (an open-source Nested Arabic Named Entity Corpus) with subtypes. In particular, four main entity types in Wojood, geopolitical entity (GPE), location (LOC), organization (ORG), and facility (FAC), are extended with 31 subtypes. To do this, we first revised Wojood's annotations of GPE, LOC, ORG, and FAC to be compatible with the LDC's ACE guidelines, which yielded 5, 614 changes. Second, all mentions of GPE, LOC, ORG, and FAC (~44K) in Wojood are manually annotated with the LDC's ACE sub-types. We refer to this extended version of Wojood as WojoodF ine. To evaluate our annotations, we measured the inter-annotator agreement (IAA) using both Cohen's Kappa and F1 score, resulting in 0.9861 and 0.9889, respectively. To compute the baselines of WojoodF ine, we fine-tune three pre-trained Arabic BERT encoders in three settings: flat NER, nested NER and nested NER with subtypes and achieved F1 score of 0.920, 0.866, and 0.885, respectively. Our corpus and models are open-source and available at https://sina.birzeit.edu/wojood/.

Amal Nayouf, Tymaa Hammouda, Mustafa Jarrar et al.

This paper presents Nabra, a corpora of Syrian Arabic dialects with morphological annotations. A team of Syrian natives collected more than 6K sentences containing about 60K words from several sources including social media posts, scripts of movies and series, lyrics of songs and local proverbs to build Nabra. Nabra covers several local Syrian dialects including those of Aleppo, Damascus, Deir-ezzur, Hama, Homs, Huran, Latakia, Mardin, Raqqah, and Suwayda. A team of nine annotators annotated the 60K tokens with full morphological annotations across sentence contexts. We trained the annotators to follow methodological annotation guidelines to ensure unique morpheme annotations, and normalized the annotations. F1 and kappa agreement scores ranged between 74% and 98% across features, showing the excellent quality of Nabra annotations. Our corpora are open-source and publicly available as part of the Currasat portal https://sina.birzeit.edu/currasat.

Mustafa Jarrar, Mohammed Khalilia, Sana Ghanem

This paper presents Wojood, a corpus for Arabic nested Named Entity Recognition (NER). Nested entities occur when one entity mention is embedded inside another entity mention. Wojood consists of about 550K Modern Standard Arabic (MSA) and dialect tokens that are manually annotated with 21 entity types including person, organization, location, event and date. More importantly, the corpus is annotated with nested entities instead of the more common flat annotations. The data contains about 75K entities and 22.5% of which are nested. The inter-annotator evaluation of the corpus demonstrated a strong agreement with Cohen's Kappa of 0.979 and an F1-score of 0.976. To validate our data, we used the corpus to train a nested NER model based on multi-task learning and AraBERT (Arabic BERT). The model achieved an overall micro F1-score of 0.884. Our corpus, the annotation guidelines, the source code and the pre-trained model are publicly available.

Mustafa Jarrar

We present a formal Arabic wordnet built on the basis of a carefully designed ontology hereby referred to as the Arabic Ontology. The ontology provides a formal representation of the concepts that the Arabic terms convey, and its content was built with ontological analysis in mind, and benchmarked to scientific advances and rigorous knowledge sources as much as this is possible, rather than to only speakers' beliefs as lexicons typically are. A comprehensive evaluation was conducted thereby demonstrating that the current version of the top-levels of the ontology can top the majority of the Arabic meanings. The ontology consists currently of about 1,300 well-investigated concepts in addition to 11,000 concepts that are partially validated. The ontology is accessible and searchable through a lexicographic search engine (https://ontology.birzeit.edu) that also includes about 150 Arabic-multilingual lexicons, and which are being mapped and enriched using the ontology. The ontology is fully mapped with Princeton WordNet, Wikidata, and other resources.

Moustafa Al-Hajj, Mustafa Jarrar

Using pre-trained transformer models such as BERT has proven to be effective in many NLP tasks. This paper presents our work to fine-tune BERT models for Arabic Word Sense Disambiguation (WSD). We treated the WSD task as a sentence-pair binary classification task. First, we constructed a dataset of labeled Arabic context-gloss pairs (~167k pairs) we extracted from the Arabic Ontology and the large lexicographic database available at Birzeit University. Each pair was labeled as True or False and target words in each context were identified and annotated. Second, we used this dataset for fine-tuning three pre-trained Arabic BERT models. Third, we experimented the use of different supervised signals used to emphasize target words in context. Our experiments achieved promising results (accuracy of 84%) although we used a large set of senses in the experiment.

Karim El Haff, Mustafa Jarrar, Tymaa Hammouda et al.

The processing of the Arabic language is a complex field of research. This is due to many factors, including the complex and rich morphology of Arabic, its high degree of ambiguity, and the presence of several regional varieties that need to be processed while taking into account their unique characteristics. When its dialects are taken into account, this language pushes the limits of NLP to find solutions to problems posed by its inherent nature. It is a diglossic language; the standard language is used in formal settings and in education and is quite different from the vernacular languages spoken in the different regions and influenced by older languages that were historically spoken in those regions. This should encourage NLP specialists to create dialect-specific corpora such as the Palestinian morphologically annotated Curras corpus of Birzeit University. In this work, we present the Lebanese Corpus Baladi that consists of around 9.6K morphologically annotated tokens. Since Lebanese and Palestinian dialects are part of the same Levantine dialectal continuum, and thus highly mutually intelligible, our proposed corpus was constructed to be used to (1) enrich Curras and transform it into a more general Levantine corpus and (2) improve Curras by solving detected errors.

Lina Duaibes, Areej Jaber, Mustafa Jarrar et al.

The proliferation of bias and propaganda on social media is an increasingly significant concern, leading to the development of techniques for automatic detection. This article presents a multilingual corpus of 12, 000 Facebook posts fully annotated for bias and propaganda. The corpus was created as part of the FigNews 2024 Shared Task on News Media Narratives for framing the Israeli War on Gaza. It covers various events during the War from October 7, 2023 to January 31, 2024. The corpus comprises 12, 000 posts in five languages (Arabic, Hebrew, English, French, and Hindi), with 2, 400 posts for each language. The annotation process involved 10 graduate students specializing in Law. The Inter-Annotator Agreement (IAA) was used to evaluate the annotations of the corpus, with an average IAA of 80.8% for bias and 70.15% for propaganda annotations. Our team was ranked among the bestperforming teams in both Bias and Propaganda subtasks. The corpus is open-source and available at https://sina.birzeit.edu/fada

Wajdi Zaghouani, Mustafa Jarrar, Nizar Habash et al.

We present an overview of the FIGNEWS shared task, organized as part of the ArabicNLP 2024 conference co-located with ACL 2024. The shared task addresses bias and propaganda annotation in multilingual news posts. We focus on the early days of the Israel War on Gaza as a case study. The task aims to foster collaboration in developing annotation guidelines for subjective tasks by creating frameworks for analyzing diverse narratives highlighting potential bias and propaganda. In a spirit of fostering and encouraging diversity, we address the problem from a multilingual perspective, namely within five languages: English, French, Arabic, Hebrew, and Hindi. A total of 17 teams participated in two annotation subtasks: bias (16 teams) and propaganda (6 teams). The teams competed in four evaluation tracks: guidelines development, annotation quality, annotation quantity, and consistency. Collectively, the teams produced 129,800 data points. Key findings and implications for the field are discussed.

Sanad Malaysha, Mo El-Haj, Saad Ezzini et al.

The expanding financial markets of the Arab world require sophisticated Arabic NLP tools. To address this need within the banking domain, the Arabic Financial NLP (AraFinNLP) shared task proposes two subtasks: (i) Multi-dialect Intent Detection and (ii) Cross-dialect Translation and Intent Preservation. This shared task uses the updated ArBanking77 dataset, which includes about 39k parallel queries in MSA and four dialects. Each query is labeled with one or more of a common 77 intents in the banking domain. These resources aim to foster the development of robust financial Arabic NLP, particularly in the areas of machine translation and banking chat-bots. A total of 45 unique teams registered for this shared task, with 11 of them actively participated in the test phase. Specifically, 11 teams participated in Subtask 1, while only 1 team participated in Subtask 2. The winning team of Subtask 1 achieved F1 score of 0.8773, and the only team submitted in Subtask 2 achieved a 1.667 BLEU score.

Sana Ghanem, Mustafa Jarrar, Radi Jarrar et al.

This paper addresses the task of extending a given synset with additional synonyms taking into account synonymy strength as a fuzzy value. Given a mono/multilingual synset and a threshold (a fuzzy value [0-1]), our goal is to extract new synonyms above this threshold from existing lexicons. We present twofold contributions: an algorithm and a benchmark dataset. The dataset consists of 3K candidate synonyms for 500 synsets. Each candidate synonym is annotated with a fuzzy value by four linguists. The dataset is important for (i) understanding how much linguists (dis/)agree on synonymy, in addition to (ii) using the dataset as a baseline to evaluate our algorithm. Our proposed algorithm extracts synonyms from existing lexicons and computes a fuzzy value for each candidate. Our evaluations show that the algorithm behaves like a linguist and its fuzzy values are close to those proposed by linguists (using RMSE and MAE). The dataset and a demo page are publicly available at https://portal.sina.birzeit.edu/synonyms.

Mohammed Khalilia, Sanad Malaysha, Reem Suwaileh et al.

This paper presents an overview of the Arabic Natural Language Understanding (ArabicNLU 2024) shared task, focusing on two subtasks: Word Sense Disambiguation (WSD) and Location Mention Disambiguation (LMD). The task aimed to evaluate the ability of automated systems to resolve word ambiguity and identify locations mentioned in Arabic text. We provided participants with novel datasets, including a sense-annotated corpus for WSD, called SALMA with approximately 34k annotated tokens, and the IDRISI-DA dataset with 3,893 annotations and 763 unique location mentions. These are challenging tasks. Out of the 38 registered teams, only three teams participated in the final evaluation phase, with the highest accuracy being 77.8% for WSD and the highest MRR@1 being 95.0% for LMD. The shared task not only facilitated the evaluation and comparison of different techniques, but also provided valuable insights and resources for the continued advancement of Arabic NLU technologies.

Sanad Malaysha, Mustafa Jarrar, Mohammed Khalilia

Arabic language lacks semantic datasets and sense inventories. The most common semantically-labeled dataset for Arabic is the ArabGlossBERT, a relatively small dataset that consists of 167K context-gloss pairs (about 60K positive and 107K negative pairs), collected from Arabic dictionaries. This paper presents an enrichment to the ArabGlossBERT dataset, by augmenting it using (Arabic-English-Arabic) machine back-translation. Augmentation increased the dataset size to 352K pairs (149K positive and 203K negative pairs). We measure the impact of augmentation using different data configurations to fine-tune BERT on target sense verification (TSV) task. Overall, the accuracy ranges between 78% to 84% for different data configurations. Although our approach performed at par with the baseline, we did observe some improvements for some POS tags in some experiments. Furthermore, our fine-tuned models are trained on a larger dataset covering larger vocabulary and contexts. We provide an in-depth analysis of the accuracy for each part-of-speech (POS).

Eman Naser-Karajah, Nabil Arman, Mustafa Jarrar

Extracting synonyms from dictionaries or corpora is gaining special attention as synonyms play an important role in improving NLP application performance. This paper presents a survey of the different approaches and trends used in automatically extracting the synonyms. These approaches can be divided into four main categories. The first approach is to find the Synonyms using a translation graph. The second approach is to discover new transition pairs such as (Arabic-English) (English-France) then (Arabic-France). The third approach is to construct new WordNets by exploring synonymy graphs, and the fourth approach is to find similar words from corpora using Deep Learning methods, such as word embeddings and recently BERT models. The paper also presents a comparative analysis between these approaches and highlights potential adaptation to generate synonyms automatically in the Arabic language as future work.

Mustafa Jarrar, Muhammad Abdul-Mageed, Mohammed Khalilia et al.

We present WojoodNER-2023, the first Arabic Named Entity Recognition (NER) Shared Task. The primary focus of WojoodNER-2023 is on Arabic NER, offering novel NER datasets (i.e., Wojood) and the definition of subtasks designed to facilitate meaningful comparisons between different NER approaches. WojoodNER-2023 encompassed two Subtasks: FlatNER and NestedNER. A total of 45 unique teams registered for this shared task, with 11 of them actively participating in the test phase. Specifically, 11 teams participated in FlatNER, while $8$ teams tackled NestedNER. The winning teams achieved F1 scores of 91.96 and 93.73 in FlatNER and NestedNER, respectively.

Mustafa Jarrar, Nagham Hamad, Mohammed Khalilia et al.

We present WojoodNER-2024, the second Arabic Named Entity Recognition (NER) Shared Task. In WojoodNER-2024, we focus on fine-grained Arabic NER. We provided participants with a new Arabic fine-grained NER dataset called wojoodfine, annotated with subtypes of entities. WojoodNER-2024 encompassed three subtasks: (i) Closed-Track Flat Fine-Grained NER, (ii) Closed-Track Nested Fine-Grained NER, and (iii) an Open-Track NER for the Israeli War on Gaza. A total of 43 unique teams registered for this shared task. Five teams participated in the Flat Fine-Grained Subtask, among which two teams tackled the Nested Fine-Grained Subtask and one team participated in the Open-Track NER Subtask. The winning teams achieved F-1 scores of 91% and 92% in the Flat Fine-Grained and Nested Fine-Grained Subtasks, respectively. The sole team in the Open-Track Subtask achieved an F-1 score of 73.7%.

Nagham Hamad, Mustafa Jarrar, Mohammad Khalilia et al.

Offensive language detection has been well studied in many languages, but it is lagging behind in low-resource languages, such as Hebrew. In this paper, we present a new offensive language corpus in Hebrew. A total of 15,881 tweets were retrieved from Twitter. Each was labeled with one or more of five classes (abusive, hate, violence, pornographic, or none offensive) by Arabic-Hebrew bilingual speakers. The annotation process was challenging as each annotator is expected to be familiar with the Israeli culture, politics, and practices to understand the context of each tweet. We fine-tuned two Hebrew BERT models, HeBERT and AlephBERT, using our proposed dataset and another published dataset. We observed that our data boosts HeBERT performance by 2% when combined with D_OLaH. Fine-tuning AlephBERT on our data and testing on D_OLaH yields 69% accuracy, while fine-tuning on D_OLaH and testing on our data yields 57% accuracy, which may be an indication to the generalizability our data offers. Our dataset and fine-tuned models are available on GitHub and Huggingface.

Gagan Bhatia, Hamdy Mubarak, Mustafa Jarrar et al.

LLMs are increasingly used for Islamic question answering, where ungrounded responses may carry serious religious consequences. Yet standard MCQ/MRC-style evaluations do not capture key real-world failure modes, notably free-form hallucinations and whether models appropriately abstain when evidence is lacking. To shed a light on this aspect we introduce ISLAMICFAITHQA, a 3,810-item bilingual (Arabic/English) generative benchmark with atomic single-gold answers, which enables direct measurement of hallucination and abstention. We additionally developed an end-to-end grounded Islamic modelling suite consisting of (i) 25K Arabic text-grounded SFT reasoning pairs, (ii) 5K bilingual preference samples for reward-guided alignment, and (iii) a verse-level Qur'an retrieval corpus of $\sim$6k atomic verses (ayat). Building on these resources, we develop an agentic Quran-grounding framework (agentic RAG) that uses structured tool calls for iterative evidence seeking and answer revision. Experiments across Arabic-centric and multilingual LLMs show that retrieval improves correctness and that agentic RAG yields the largest gains beyond standard RAG, achieving state-of-the-art performance and stronger Arabic-English robustness even with a small model (i.e., Qwen3 4B). We will make the experimental resources and datasets publicly available for the community.

Mustafa Jarrar, Ahmet Birim, Mohammed Khalilia et al.

This paper presents the ArBanking77, a large Arabic dataset for intent detection in the banking domain. Our dataset was arabized and localized from the original English Banking77 dataset, which consists of 13,083 queries to ArBanking77 dataset with 31,404 queries in both Modern Standard Arabic (MSA) and Palestinian dialect, with each query classified into one of the 77 classes (intents). Furthermore, we present a neural model, based on AraBERT, fine-tuned on ArBanking77, which achieved an F1-score of 0.9209 and 0.8995 on MSA and Palestinian dialect, respectively. We performed extensive experimentation in which we simulated low-resource settings, where the model is trained on a subset of the data and augmented with noisy queries to simulate colloquial terms, mistakes and misspellings found in real NLP systems, especially live chat queries. The data and the models are publicly available at https://sina.birzeit.edu/arbanking77.

Alaa Aljabari, Lina Duaibes, Mustafa Jarrar et al.

Event-argument extraction is a challenging task, particularly in Arabic due to sparse linguistic resources. To fill this gap, we introduce the \hadath corpus ($550$k tokens) as an extension of Wojood, enriched with event-argument annotations. We used three types of event arguments: $agent$, $location$, and $date$, which we annotated as relation types. Our inter-annotator agreement evaluation resulted in $82.23\%$ $Kappa$ score and $87.2\%$ $F_1$-score. Additionally, we propose a novel method for event relation extraction using BERT, in which we treat the task as text entailment. This method achieves an $F_1$-score of $94.01\%$. To further evaluate the generalization of our proposed method, we collected and annotated another out-of-domain corpus (about $80$k tokens) called \testNLI and used it as a second test set, on which our approach achieved promising results ($83.59\%$ $F_1$-score). Last but not least, we propose an end-to-end system for event-arguments extraction. This system is implemented as part of SinaTools, and both corpora are publicly available at {\small \url{https://sina.birzeit.edu/wojood}}

Fakhraddin Alwajih, Abdellah El Mekki, Samar Mohamed Magdy et al.

As large language models (LLMs) become increasingly integrated into daily life, ensuring their cultural sensitivity and inclusivity is paramount. We introduce our dataset, a year-long community-driven project covering all 22 Arab countries. The dataset includes instructions (input, response pairs) in both Modern Standard Arabic (MSA) and dialectal Arabic (DA), spanning 20 diverse topics. Built by a team of 44 researchers across the Arab world, all of whom are authors of this paper, our dataset offers a broad, inclusive perspective. We use our dataset to evaluate the cultural and dialectal capabilities of several frontier LLMs, revealing notable limitations. For instance, while closed-source LLMs generally exhibit strong performance, they are not without flaws, and smaller open-source models face greater challenges. Moreover, certain countries (e.g., Egypt, the UAE) appear better represented than others (e.g., Iraq, Mauritania, Yemen). Our annotation guidelines, code, and data for reproducibility are publicly available.

Nagham Hamad, Mohammed Khalilia, Mustafa Jarrar

We introduce Konooz, a novel multi-dimensional corpus covering 16 Arabic dialects across 10 domains, resulting in 160 distinct corpora. The corpus comprises about 777k tokens, carefully collected and manually annotated with 21 entity types using both nested and flat annotation schemes - using the Wojood guidelines. While Konooz is useful for various NLP tasks like domain adaptation and transfer learning, this paper primarily focuses on benchmarking existing Arabic Named Entity Recognition (NER) models, especially cross-domain and cross-dialect model performance. Our benchmarking of four Arabic NER models using Konooz reveals a significant drop in performance of up to 38% when compared to the in-distribution data. Furthermore, we present an in-depth analysis of domain and dialect divergence and the impact of resource scarcity. We also measured the overlap between domains and dialects using the Maximum Mean Discrepancy (MMD) metric, and illustrated why certain NER models perform better on specific dialects and domains. Konooz is open-source and publicly available at https://sina.birzeit.edu/wojood/#download

Diyam Akra, Tymaa Hammouda, Mustafa Jarrar

We present the QuranMorph corpus, a morphologically annotated corpus for the Quran (77,429 tokens). Each token in the QuranMorph was manually lemmatized and tagged with its part-of-speech by three expert linguists. The lemmatization process utilized lemmas from Qabas, an Arabic lexicographic database linked with 110 lexicons and corpora of 2 million tokens. The part-of-speech tagging was performed using the fine-grained SAMA/Qabas tagset, which encompasses 40 tags. As shown in this paper, this rich lemmatization and POS tagset enabled the QuranMorph corpus to be inter-linked with many linguistic resources. The corpus is open-source and publicly available as part of the SinaLab resources at (https://sina.birzeit.edu/quran)

Tymaa Hammouda, Mustafa Jarrar, Mohammed Khalilia

We introduce SinaTools, an open-source Python package for Arabic natural language processing and understanding. SinaTools is a unified package allowing people to integrate it into their system workflow, offering solutions for various tasks such as flat and nested Named Entity Recognition (NER), fully-flagged Word Sense Disambiguation (WSD), Semantic Relatedness, Synonymy Extractions and Evaluation, Lemmatization, Part-of-speech Tagging, Root Tagging, and additional helper utilities such as corpus processing, text stripping methods, and diacritic-aware word matching. This paper presents SinaTools and its benchmarking results, demonstrating that SinaTools outperforms all similar tools on the aforementioned tasks, such as Flat NER (87.33%), Nested NER (89.42%), WSD (82.63%), Semantic Relatedness (0.49 Spearman rank), Lemmatization (90.5%), POS tagging (97.5%), among others. SinaTools can be downloaded from (https://sina.birzeit.edu/sinatools).

Mustafa Jarrar, Tymaa Hammouda

We present Qabas, a novel open-source Arabic lexicon designed for NLP applications. The novelty of Qabas lies in its synthesis of 110 lexicons. Specifically, Qabas lexical entries (lemmas) are assembled by linking lemmas from 110 lexicons. Furthermore, Qabas lemmas are also linked to 12 morphologically annotated corpora (about 2M tokens), making it the first Arabic lexicon to be linked to lexicons and corpora. Qabas was developed semi-automatically, utilizing a mapping framework and a web-based tool. Compared with other lexicons, Qabas stands as the most extensive Arabic lexicon, encompassing about 58K lemmas (45K nominal lemmas, 12.5K verbal lemmas, and 473 functional-word lemmas). Qabas is open-source and accessible online at https://sina.birzeit.edu/qabas.

Sanad Malaysha, Mustafa Jarrar, Mohammed Khalilia

Semantic textual relatedness is a broader concept of semantic similarity. It measures the extent to which two chunks of text convey similar meaning or topics, or share related concepts or contexts. This notion of relatedness can be applied in various applications, such as document clustering and summarizing. SemRel-2024, a shared task in SemEval-2024, aims at reducing the gap in the semantic relatedness task by providing datasets for fourteen languages and dialects including Arabic. This paper reports on our participation in Track A (Algerian and Moroccan dialects) and Track B (Modern Standard Arabic). A BERT-based model is augmented and fine-tuned for regression scoring in supervised track (A), while BERT-based cosine similarity is employed for unsupervised track (B). Our system ranked 1st in SemRel-2024 for MSA with a Spearman correlation score of 0.49. We ranked 5th for Moroccan and 12th for Algerian with scores of 0.83 and 0.53, respectively.

Bashar Talafha, Hawau Olamide Toyin, Peter Sullivan et al.

We present the findings of the sixth Nuanced Arabic Dialect Identification (NADI 2025) Shared Task, which focused on Arabic speech dialect processing across three subtasks: spoken dialect identification (Subtask 1), speech recognition (Subtask 2), and diacritic restoration for spoken dialects (Subtask 3). A total of 44 teams registered, and during the testing phase, 100 valid submissions were received from eight unique teams. The distribution was as follows: 34 submissions for Subtask 1 "five teamsæ, 47 submissions for Subtask 2 "six teams", and 19 submissions for Subtask 3 "two teams". The best-performing systems achieved 79.8% accuracy on Subtask 1, 35.68/12.20 WER/CER (overall average) on Subtask 2, and 55/13 WER/CER on Subtask 3. These results highlight the ongoing challenges of Arabic dialect speech processing, particularly in dialect identification, recognition, and diacritic restoration. We also summarize the methods adopted by participating teams and briefly outline directions for future editions of NADI.

Fakhraddin Alwajih, Samar M. Magdy, Abdellah El Mekki et al.

Mainstream large vision-language models (LVLMs) inherently encode cultural biases, highlighting the need for diverse multimodal datasets. To address this gap, we introduce PEARL, a large-scale Arabic multimodal dataset and benchmark explicitly designed for cultural understanding. Constructed through advanced agentic workflows and extensive human-in-the-loop annotations by 37 annotators from across the Arab world, PEARL comprises over 309K multimodal examples spanning ten culturally significant domains covering all Arab countries. We further provide two robust evaluation benchmarks (PEARL and PEARL-LITE) along with a specialized subset (PEARL-X) explicitly developed to assess nuanced cultural variations. Comprehensive evaluations on state-of-the-art open and proprietary LVLMs demonstrate that reasoning-centric instruction alignment substantially improves models' cultural grounding compared to conventional scaling methods. PEARL establishes a foundational resource for advancing culturally-informed multimodal modeling research. All datasets and benchmarks are publicly available.

Abdellah El Mekki, Samar M. Magdy, Houdaifa Atou et al.

Arabic is a highly diglossic language where most daily communication occurs in regional dialects rather than Modern Standard Arabic. Despite this, machine translation (MT) systems often generalize poorly to dialectal input, limiting their utility for millions of speakers. We introduce \textbf{Alexandria}, a large-scale, community-driven, human-translated dataset designed to bridge this gap. Alexandria covers 13 Arab countries and 11 high-impact domains, including health, education, and agriculture. Unlike previous resources, Alexandria provides unprecedented granularity by associating contributions with city-of-origin metadata, capturing authentic local varieties beyond coarse regional labels. The dataset consists of multi-turn conversational scenarios annotated with speaker-addressee gender configurations, enabling the study of gender-conditioned variation in dialectal use. Comprising 107K total samples, Alexandria serves as both a training resource and a rigorous benchmark for evaluating MT and Large Language Models (LLMs). Our automatic and human evaluation of Arabic-aware LLMs benchmarks current capabilities in translating across diverse Arabic dialects and sub-dialects, while exposing significant persistent challenges.

Sylvio Barbon Junior, Paolo Ceravolo, Sven Groppe et al.

A Language Model is a term that encompasses various types of models designed to understand and generate human communication. Large Language Models (LLMs) have gained significant attention due to their ability to process text with human-like fluency and coherence, making them valuable for a wide range of data-related tasks fashioned as pipelines. The capabilities of LLMs in natural language understanding and generation, combined with their scalability, versatility, and state-of-the-art performance, enable innovative applications across various AI-related fields, including eXplainable Artificial Intelligence (XAI), Automated Machine Learning (AutoML), and Knowledge Graphs (KG). Furthermore, we believe these models can extract valuable insights and make data-driven decisions at scale, a practice commonly referred to as Big Data Analytics (BDA). In this position paper, we provide some discussions in the direction of unlocking synergies among these technologies, which can lead to more powerful and intelligent AI solutions, driving improvements in data pipelines across a wide range of applications and domains integrating humans, computers, and knowledge.

Moustafa Al-Hajj, Mustafa Jarrar

This paper presents a set of experiments to evaluate and compare between the performance of using CBOW Word2Vec and Lemma2Vec models for Arabic Word-in-Context (WiC) disambiguation without using sense inventories or sense embeddings. As part of the SemEval-2021 Shared Task 2 on WiC disambiguation, we used the dev.ar-ar dataset (2k sentence pairs) to decide whether two words in a given sentence pair carry the same meaning. We used two Word2Vec models: Wiki-CBOW, a pre-trained model on Arabic Wikipedia, and another model we trained on large Arabic corpora of about 3 billion tokens. Two Lemma2Vec models was also constructed based on the two Word2Vec models. Each of the four models was then used in the WiC disambiguation task, and then evaluated on the SemEval-2021 test.ar-ar dataset. At the end, we reported the performance of different models and compared between using lemma-based and word-based models.

Mustafa Jarrar, Eman Karajah, Muhammad Khalifa et al.

We present our progress in developing a novel algorithm to extract synonyms from bilingual dictionaries. Identification and usage of synonyms play a significant role in improving the performance of information access applications. The idea is to construct a translation graph from translation pairs, then to extract and consolidate cyclic paths to form bilingual sets of synonyms. The initial evaluation of this algorithm illustrates promising results in extracting Arabic-English bilingual synonyms. In the evaluation, we first converted the synsets in the Arabic WordNet into translation pairs (i.e., losing word-sense memberships). Next, we applied our algorithm to rebuild these synsets. We compared the original and extracted synsets obtaining an F-Measure of 82.3% and 82.1% for Arabic and English synsets extraction, respectively.

Kareem Darwish, Nizar Habash, Mourad Abbas et al.

The term natural language refers to any system of symbolic communication (spoken, signed or written) without intentional human planning and design. This distinguishes natural languages such as Arabic and Japanese from artificially constructed languages such as Esperanto or Python. Natural language processing (NLP) is the sub-field of artificial intelligence (AI) focused on modeling natural languages to build applications such as speech recognition and synthesis, machine translation, optical character recognition (OCR), sentiment analysis (SA), question answering, dialogue systems, etc. NLP is a highly interdisciplinary field with connections to computer science, linguistics, cognitive science, psychology, mathematics and others. Some of the earliest AI applications were in NLP (e.g., machine translation); and the last decade (2010-2020) in particular has witnessed an incredible increase in quality, matched with a rise in public awareness, use, and expectations of what may have seemed like science fiction in the past. NLP researchers pride themselves on developing language independent models and tools that can be applied to all human languages, e.g. machine translation systems can be built for a variety of languages using the same basic mechanisms and models. However, the reality is that some languages do get more attention (e.g., English and Chinese) than others (e.g., Hindi and Swahili). Arabic, the primary language of the Arab world and the religious language of millions of non-Arab Muslims is somewhere in the middle of this continuum. Though Arabic NLP has many challenges, it has seen many successes and developments. Next we discuss Arabic's main challenges as a necessary background, and we present a brief history of Arabic NLP. We then survey a number of its research areas, and close with a critical discussion of the future of Arabic NLP.