New publications at ArabicNLP 2026 Shared Tasks

@inproceedings{Verma:et:al:2026:CLASP,
  title     = {{TTL}ab at {S}tance{E}val-2026: A Cloze-Style Prompting Approach
               for {A}rabic-Language Stance Detection ({CLASP}-Ar)},
  author    = {Verma, Bhuvanesh and Abusaleh, Ali and Mehler, Alexander},
  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: Shared Tasks},
  month     = {oct},
  year      = {2026},
  address   = {Budapest, Hungary},
  publisher = {Association for Computational Linguistics},
  url       = {https://aclanthology.org/2026.arabicnlp-sharedtasks.66/},
  pages     = {511--518},
  isbn      = {979-8-89176-497-2},
  abstract  = {Arabic-language stance detection remains challenging, and previous
               shared-task systems have largely relied on multitask learning
               and ensembles. While these systems achieve state-of-the-art performance,
               their applicability and transferability are limited by the additional
               complexity introduced by multitask learning. To reduce this complexity,
               we introduce $\\texttt{CLASP-Ar}$, which reformulates the task
               as cloze-style masked language modeling. In this approach, the
               target, predicted sentiment, and text are combined into a single
               prompt whose $\\texttt{[MASK]}$ prediction is restricted to a
               verbalizer-constrained label vocabulary. When evaluated on the
               StanceEval-2026: Arabic Stance Detection Shared Task, our proposed
               approach achieves an $F_{\\text{avg2}}$ score of 71.36{\\%} on
               Track 1 and 74.14{\\%} on Track 2 test sets.}
}

@inproceedings{Abusaleh:et:al:2026:mt,
  title     = {{TTL}ab at {A}lexandria{X}-2026: A Fine-Tuned Surface Tagger for
               {A}rabic Machine-Translation Error-Span Detection and Classification},
  author    = {Abusaleh, Ali and Verma, Bhuvanesh and Mehler, Alexander},
  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: Shared Tasks},
  month     = {oct},
  year      = {2026},
  address   = {Budapest, Hungary},
  publisher = {Association for Computational Linguistics},
  url       = {https://aclanthology.org/2026.arabicnlp-sharedtasks.98/},
  pages     = {786--792},
  isbn      = {979-8-89176-497-2},
  abstract  = {We present TTLab{'}s submission to the AlexandriaX-2026 Subtask
               3 on Arabic MT error span detection and classification. Our system
               frames the task as token-level classification over surface forms,
               preserving character offsets to ensure exact alignment with the
               evaluation metric. To handle severe label imbalance, we employ
               a focal loss with class weighting and dialect-specific decoding
               thresholds. Among six Arabic pre-trained encoders, MARBERTv2 achieves
               the best overall performance of 40.8 and 40.91 on the development
               and test set, respectively, ranking 3rd out of all participating
               teams. While our system localizes error spans effectively, classification
               of rare error types remains challenging, highlighting the need
               for data augmentation for tail categories.}
}

@inproceedings{verma-etal-2026-ttlab-daleel,
  title     = {{TTL}ab at Daleel 2026: {STAR}-Ar, Sequence Tagging for Argument
               Recognition in {A}rabic},
  author    = {Verma, Bhuvanesh and Abusaleh, Ali and Mehler, Alexander},
  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: Shared Tasks},
  month     = {oct},
  year      = {2026},
  address   = {Budapest, Hungary},
  publisher = {Association for Computational Linguistics},
  url       = {https://aclanthology.org/2026.arabicnlp-sharedtasks.163/},
  pages     = {1304--1309},
  isbn      = {979-8-89176-497-2},
  abstract  = {Argument Mining (AM) is a critical NLP task that remains significantly
               under-resourced in Arabic. This paper presents STAR-Ar, a BERT-BiLSTM-CRF
               architecture for argument discourse detection and classification,
               as our system for Daleel 2026, the inaugural Arabic argument mining
               shared task. The task requires the identification and classification
               of argumentative discourse units (ADUs) in debate and editorial
               texts. We jointly model these two objectives as a token-level
               sequence labeling task using a BERT-BiLSTM-CRF architecture that
               combines contextual transformer embeddings with structural transition
               constraints to support accurate span detection. STAR-Ar achieves
               an F1-score of 72.69 on validation and 73.7 on test data. Our
               domain-specific analysis shows that models trained exclusively
               on editorials underperform those trained on debates, a disparity
               we primarily attribute to the smaller size of the editorial dataset.}
}