Morocco

Optimizer choice is a central hyperparameter in fine-tuning transformer models, yet its impact remains under-studied for Arabic-script social media classification under class imbalance. We compare Adam, AdamW, and SGD for fine-tuning QARiB on two Arabic offensive-language benchmarks, OffensEval20 and MPOLD, using a controlled grid over learning rate, weight decay, and warmup, and report test-set performance as mean (std) over three random seeds.

Minority-class discrimination is evaluated using macro-F1 and AUC-PROFF, while calibration is assessed via expected calibration error (ECE) and reliability diagrams. Across both datasets, AdamW and Adam are consistently strong and closely matched when properly tuned, whereas SGD substantially underperforms under the same tuning budget and exhibits higher seed sensitivity.

We observe non-trivial miscalibration across optimizers; post-hoc temperature scaling offers a low-cost adjustment, yielding modest, dataset-dependent changes in ECE while preserving ranking-based discrimination. In practice, for Arabic offensive-language detection under imbalance, we recommend starting from a tuned AdamW or Adam baseline; when calibrated probabilities are required for thresholding or triage, temperature scaling can be applied. We will release a reproducible pipeline to support further evaluation of optimizer–calibration trade-offs in Arabic-script safety tasks.

EACL 2026

Optimizer Choice and Calibration for QARiB on Arabic-Script Social Media Offensive Language Detection

qarib

optimizer choice

temperature scaling

arabic offensive language detection

calibration

class imbalance

**Welcome to EMNLP 2023!**

On behalf of the EMNLP 2023 Organizing Committee, I extend a warm and heartfelt welcome to all of you to the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP). It is with immense pleasure and excitement that we gather here in Singapore, a vibrant hub of innovation and technological advancement.

The conference program is packed with insightful presentations, thought-provoking workshops, and engaging networking opportunities. In addition to the technical sessions, we have also planned several social events that will provide you with the opportunity to connect with your colleagues.

The conference is held in person at the Resorts World Convention Centre in Singapore, and available on-line with the help of Underline.

For those in Singapore, I hope that you will find time to explore the exciting Sentosa Island, Gardens by the Bay, Singapore Botanic Gardens and the many other attractions unique to Singapore.

Of course, we are grateful to our sponsors and partners for their generous support of EMNLP 2023, whose contributions make it possible for us to host this world-class event.

Yuji Matsumoto (RIKEN AIP) 
EMNLP 2023 General Chair

To access the **EMNLP 2023** event page on Underline, you need to register for the Conference. 
Please follow **[this link](https://2023.emnlp.org/registration/)** for more details.

EMNLP 2023

EMNLP 2023 took place in Singapore from Dec 6th to Dec 10th, 2023.

workshop paper

#### *Message from the General Chair, Aline Villavicencio*
I’m delighted and honoured to welcome you to the 19th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2026), taking place in the beautiful city of Rabat, in Morocco, in March 24-29, 2026. EACL is the flagship European conference of the Association and EACL 2026 proudly continues our field’s tradition of excellence in scholarship, innovation, and inclusivity. I am deeply grateful to the many volunteers whose dedication, generosity, and tireless efforts have made this conference possible.
For the first time EACL is being hosted in the African continent. This is an important milestone for our community, and we are grateful to our Moroccan hosts for enabling this historic moment by bringing this edition of EACL to Rabat. We are also delighted that the Second Arabic NLP School is co-located with EACL. We hope attendees enjoy this wonderful opportunity to strengthen ties with the Computational Linguistics communities across the African continent. *[Read full message](https://drive.google.com/file/d/14NlmHvwM6fPJuMmOvVh7K0vtQbEyv3SZ/view?usp=sharing)* 

<html><button style="display: inline-flex; align-items: center; justify-content: center; white-space: nowrap; border-radius: 9999px; font-weight: bold; background: #7c3aed; color: white; font-family: 'Space Grotesk', sans-serif; height: 40px; font-size: 16px; padding: 0 20px; border: none; cursor: pointer" onclick="window.open('https://underline.io/events/522/reception','_blank')">Go to Workshops and Tutorials Program</button></html>

To access this event page, you need to log in with the **email address you registered with**. Access credentials will be sent to your email from Underline - subject line "Welcome to EACL 2026". Please be sure to check your spam email folder if you do not see an email confirmation right away.

Please log in

To access this event page, you are required to register.
Please complete your registration to continue.

We recommend reading [**the registration information**](https://2026.eacl.org/registration/) first.

**Online Registration Form**: https://acl.swoogo.com/eacl2026

Registration Required

Welcome to the 19th Conference of the European Chapter of the Association for Computational Linguistics (EACL). EACL 2026 will be held in Rabat, Morocco, from March 24–29, 2026. 

Despite the advances in neural text to speech
(TTS), many Arabic dialectal varieties remain
marginally addressed, with most resources con-
centrated on Modern Spoken Arabic (MSA)
and Gulf dialects, leaving Egyptian Arabic—
the most widely understood Arabic dialect—
severely under-resourced. We address this
gap by introducing NileTTS: 38 hours of tran-
scribed speech from two speakers across di-
verse domains including medical, sales, and
general conversations. We construct this
dataset using a novel synthetic pipeline: large
language models (LLM) generate Egyptian
Arabic content, which is then converted to natu-
ral speech using audio synthesis tools, followed
by automatic transcription and speaker diariza-
tion with manual quality verification. We fine-
tune XTTS v2, a state-of-the-art multilingual
TTS model, on our dataset and evaluate against
the baseline model trained on other Arabic
dialects. Our contributions include: (1) the
first publicly available Egyptian Arabic TTS
dataset, (2) a reproducible synthetic data gen-
eration pipeline for dialectal TTS, and (3) an
open-source fine-tuned model. All resources
are released to advance Egyptian Arabic speech
synthesis research.

LLM-to-Speech: A Synthetic Data Pipeline for Training Dialectal Text-to-Speech Models

Kazakh is a Turkic language using the Arabic, Cyrillic, and Latin scripts, making it unique in terms of optical character recognition (OCR). Work on OCR for low-resource Kazakh scripts is very scarce, and no OCR benchmarks or images exist for the Arabic and Latin scripts. We construct a synthetic OCR dataset of 7,219 images for all three scripts with font, color, and noise variations to imitate real OCR tasks. We evaluated three multimodal large language models (MLLMs) on a subset of the benchmark for OCR and language identification: Gemma-3-12B-it, Qwen2.5-VL-7B-Instruct, and Llama-3.2-11B-Vision-Instruct. All models are unsuccessful with Latin and Arabic script OCR, and fail to recognize the Arabic script as Kazakh text, misclassifying it as Arabic, Farsi, and Kurdish. These findings show significant gaps in current MLLM capabilities to process low-resource Abjad-based scripts and demonstrate the need for inclusive models and benchmarks supporting low-resource scripts and languages.

KazakhOCR: A Synthetic Benchmark for Evaluating Multimodal Models in Low-Resource Kazakh Script OCR

This study addresses the task of automatic transliteration from Tajik (Cyrillic script) to Persian (Perso-Arabic script). We present a curated, lexicographically verified parallel corpus of 52,152 Tajik–Persian words and short phrases, compiled from authoritative printed dictionaries, encyclopedic sources, and manually verified online resources. To our knowledge, this is the largest high-quality word-level corpus available for transliteration research.

Using this corpus, we train a character-level sequence-to-sequence Transformer model and evaluate its performance with Character Error Rate (CER) and exact-match accuracy. The best model achieves a CER of 0.3216 and exact-match accuracy of 0.3133, outperforming both dictionary-based rule-oriented and recurrent neural models. We provide a detailed description of the data collection and preprocessing, model architecture, and experimental protocol, and we conduct a qualitative analysis of typical transliteration errors, including phonetic ambiguity, orthographic variations, and rare forms.

All preprocessing scripts, deterministic splits into training, validation, and test sets, and training configurations are released to ensure reproducibility and to support further research on the Tajik language and related Persian dialects. The corpus provides a reliable foundation for character-level transliteration and contributes to the development of applications in cross-script NLP, digital lexicography, and language learning.

Character-Level Transformer for Tajik–Persian Transliteration with a Parallel Lexical Corpus

Named Entity Recognition (NER) models trained on clean text often fail on real-world data containing orthographic noise. Work on NER for Persian is emerging, but it has not yet explored the orthographic robustness of models to perturbations often exhibited in user-generated content. We evaluate ParsBERT, ParsBERT v2.0, and BertNER on a subset of Persian-NER-Dataset-500k after applying eleven different perturbations, including simulated typos, code-switching, and segmentation errors. All models were competitive with each other, but ParsBERT v2.0 consistently displayed the best robustness to perturbations. Code-switching, typos, similar character swaps, segmentation errors, and noisy text all decreased F1 scores, while Latinized numbers increased F1 scores in ParsBERT. Removing diacritics, zero-width non-joiners, and normalizing Yeh/Kaf all did not have an effect on F1. These findings suggest that Persian NER models require improvement for performance on noisy text, and that the Perso-Arabic script introduces unique factors into NER not present in many high-resource languages, such as code-switching and Eastern Arabic numerals. This work creates a foundation for the development of robust Persian NER models and highlights the necessity of evaluating low-resource NER models under challenging and realistic conditions.

Orthographic Robustness of Persian Named Entity Recognition Models

Hausa Ajami (Hausa written in Arabic script) remains severely under-resourced for computational morphology. We present AjamiMorph, a zero-annotation framework that discovers morphemes through consensus among three unsupervised methods, viz., Byte Pair Encoding (BPE), transition-based boundary detection using Pointwise Mutual Information (PMI), and computational-linguistics-based Distributional Affix Mining (DAM).

Using a Hausa Ajami Bible corpus consisting of 637,414 tokens, AjamiMorph identifies 1,611 high-confidence morphemes, achieving 99.9% coverage. The inventory exhibits a linguistically realistic distribution (66.0% stems, 22.6% suffixes, 11.4% prefixes) and recovers 77.8% of known Hausa affixes. We also report negative results for script-driven Arabic assumptions and LLM-based approaches.

This work provides the first unsupervised morpheme inventory for Hausa Ajami and demonstrates consensus as a robust strategy for zero-resource morphology.

AjamiMorph: Zero-Annotation Morphological Discovery for Hausa Ajami via Multi-Method Consensus

As reported, approximately 6 million people in Iraq and Iran speak Sorani Kurdish, which exhibits substantial regional variation but lacks computational resources for dialect identification. We present the first fine-grained sub-dialect classification system for six Sorani varieties, viz., Sulaymaniyah, Erbil, Iranian Sorani, Ardalani, Babani, and Mukriani.

This investigation combines cross-lingual contextual embeddings (XLM-RoBERTa) with morphological features derived from explicit linguistic rules, including 24 patterns capturing verb prefixes, pronominal clitics, and definite markers. The proposed morphology-augmented XLM-R model is trained on 16,409 sentences without manual annotation and achieves 91.91% accuracy, outperforming pure transformer models (91.79%) and traditional machine-learning baselines (SVM: 86.41%).

Key ablation studies reveal that morphological features act as effective regularizers for geographically proximate dialects.

Morphological Feature Extraction for Fine-Grained Sorani Kurdish Dialect Identification: A Hybrid Transformer-Linguistic Approach

Automatic classification of literary text by historical era can support literary analysis and reveal stylistic evolution. We study this problem for Urdu poetry across three eras, classical, modern, and contemporary. We introduce a new dataset of 10,026 four-line Urdu poetry segments collected from online archives (Rekhta and UrduPoint) and labeled by era. To handle Urdu's script and orthographic variability, we apply standard preprocessing, including Unicode normalization and removal of diacritics and non-Urdu characters. We benchmark a range of approaches, from traditional machine learning classifiers to deep learning models, including four fine-tuned Urdu BERT-style transformers. To assess generalization, we evaluate under two regimes: (i) a standard stratified random split and (ii) a stricter author-disjoint split that ensures poets do not overlap between training and test sets. On the random split, the best traditional models achieve about 70–73% accuracy, suggesting era-related stylistic cues are learnable. However, performance drops to roughly 58–60% under the author-disjoint split, highlighting the difficulty in generalizing across unseen poets and the possibility of overestimating performance via author-specific leakage. Notably, fine-tuned transformers do not surpass simpler TF–IDF-based baselines, indicating that era cues may be subtle and data-limitation for complex models.

From Classical to Contemporary: Evolutionary Analysis & Classification of Urdu Poetry

Sentiment analysis in low-resource languages such as Urdu poses unique challenges due to limited annotated data, morphological complexity, and significant class imbalance in most publicly available datasets. This study addresses these issues through two experimental strategies. First, we explore class imbalance mitigation by using instruction-tuned large language models (LLMs) to generate synthetic negative sentiment samples in Urdu. This augmentation strategy results in a more balanced dataset, which significantly improves the recall and F1-score for minority class predictions when fine-tuned using a multilingual BERT model. Second, we investigate the effectiveness of translating Urdu text into English and applying sentiment classification through a pre-trained English language model. Comparative evaluation reveals that the translation-based pipeline, using a RoBERTa model fine-tuned for English sentiment classification, achieves superior performance across major metrics. Our results suggest that LLM-based augmentation and cross-lingual transfer via translation both serve as viable approaches to overcome data scarcity and performance limitations in sentiment analysis for low-resource languages. The findings provide a roadmap for scalable, language-agnostic strategies that can be extended to other under-resourced linguistic domains.

Enhancing Urdu Sentiment Classification through Instruction-Tuned LLMs and Cross-Lingual Transfer

Inserting English words, phrases, or sentences while writing or speaking in the Saudi Arabic
dialect has become a widespread phenomenon in Saudi society. This phenomenon is linguistically called code-switching. It remains unclear how current sentiment analysis methods perform on Saudi-English code-switching text. In this paper, we address this gap by conducting the first sentiment analysis study on Saudi-English code-switching text. We present the first Saudi-English Sentiment Analysis Code Switching Dataset (SESA-CSD) and establish baseline results on this dataset. By evaluating multiple state-of-the-art small language models, we achieve improvements over the baseline of 3% to 10% in both accuracy and macro-F1. Among all small language models, XLM-RoBERTa achieved the highest performance,with an accuracy of 95.50% and a macro-F1 of 95.53%. Our findings indicate that multilingual and Arabic small language models, such as XLM-RoBERTa, GigaBERT, and SaudiBERT, consistently outperform bilingual Arabic-English large language models, such as Fanar and ALLaM, across zero-shot and multiple few-shot settings.

Improving on State-of-the-Art Models for Sentiment Analysis on Saudi-English Code-Switching Text

The Arabic-derived scripts contain several languages that face challenges with the limited resources of speech detection, these challenges are worsened by the scarcity of resources and highly complex linguistic challenges. We proposed ( HACS-TL Hausa Ajami Cross-Script Transfer Learning) a brand new transformer-based architecture that focuses on the detection of hate speech within Ajami script. Hausa is a Chadic language which contains over 77 million speakers located in West Africa; it uses two types of scripts: the Latin (Boko) and the Arabic-derived Ajami which creates new computational difficulties. Our method combines scripts of artistically converted linguistics, augmented cross script multi-head attention, and dialect feature extraction to trellis the morphophonological depth of the Hausa. After a thorough examination using stratified cross-validation along with systemically augmented data, HACS-TL obtained a Macro F1 score of 76.09\% which is a significant improvement from the other multilingual baselines (mBERT (69.17 % ) XLM-RoBERTa (73.20 % ) AraBERT (58.63% ) ) HACS-TL outperformed all of the previously stated models. Strong multilingual baselines refer to the other stated models; AraBERT (58.63) XLM-RoBERTa (73.20) mBERT (69.17) HACS-TL 70.73 + 10 % Cross-Script+ (mBERT) 46.73 + 0.9 % Cross-Script + AraBERT. The importance of cross-script attention and learning from transfer sources of resources to languages with limited scripts has proven effective. Our systematic method has aided the advancement of Arabic script homage Hausa and African language resources for the NLP of the Nubians in learning African languages and the intricate Nubian and cross-learning systems from different scripts.

Downloads

Next from EACL 2026

LLM-to-Speech: A Synthetic Data Pipeline for Training Dialectal Text-to-Speech Models

Similar lecture

Adversarial Robustness of Transformer-based Arabic Offensive Language Detectors

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from EACL 2026

LLM-to-Speech: A Synthetic Data Pipeline for Training Dialectal Text-to-Speech Models

Similar lecture

Adversarial Robustness of Transformer-based Arabic Offensive Language Detectors

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads