--- title: "Bangor University at WojoodNER 2024: Advancing Arabic" description: "This paper reports Bangor University's entry to Subtask-1 of the WojoodNER 2024 shared task: closed-track, flat… 86.45% F1. 8 references." authors: ["Norah Alshammari"] year: 2024 venue: "Proceedings of the Second Arabic Natural Language Processing Conference" source: "https://aclanthology.org/2024.arabicnlp-1.105/" doi: "10.18653/v1/2024.arabicnlp-1.105" licence: "CC BY 4.0 (ACL Anthology)" licence_url: "https://creativecommons.org/licenses/by/4.0/" summary_licence: "Elamur Cosmic License" canonical: "https://research.elamur.ai/free/en/papers/alshammari-2024-bangor-university-wojoodner-2024-advancing/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/alshammari-2024-bangor-university-wojoodner-2024-advancing/) [home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2024](https://md.research.elamur.ai/free/en/papers/2024/page/14/) / Bangor University at WojoodNER 2024: Advancing Arabic Named Entity Recognition with CAMeLBERT-Mix # Bangor University at WojoodNER 2024: Advancing Arabic Named Entity Recognition with CAMeLBERT-Mix **Authors:** Norah Alshammari · **Year:** 2024 · **Venue:** [Proceedings of the Second Arabic Natural Language Processing Conference](https://md.research.elamur.ai/free/en/venues/arabicnlp/) ([ArabicNLP 2024](https://md.research.elamur.ai/free/en/venues/arabicnlp/2024/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/) **Links:** [Publisher's page](https://aclanthology.org/2024.arabicnlp-1.105/) · [PDF](https://aclanthology.org/2024.arabicnlp-1.105.pdf) · [DOI 10.18653/v1/2024.arabicnlp-1.105](https://doi.org/10.18653/v1/2024.arabicnlp-1.105) · [OpenAlex](https://openalex.org/W4402671150) **Citations:** 3 citations (OpenAlex, 2026-10-14) ## Summary This paper reports Bangor University's entry to Subtask-1 of the WojoodNER 2024 shared task: closed-track, flat, fine-grained Arabic NER. Arabic is hard for NER because it has no capitalization, rich morphology and many dialects. The task's Wojood-Fine corpus adds many entity subtypes. The authors fine-tuned the pre-trained CAMeL-Lab model bert-base-arabic-camelbert-mix with a single linear layer on top. That layer assigns each token one of 51 entity types/subtypes or the non-entity 'O' tag, using BIO-style tagging. Subword tokens are aligned to word labels. Training used cross-entropy loss and AdamW, and the checkpoint with the lowest validation loss was kept. On the blind test set the system scored 86.45% F1, against 95.87% on training data and 89.16% on validation. This places it below the organizers' baseline (89) and the top team (91). The work is mainly useful as a plain, reproducible fine-tuning reference point. Its train–validation gap shows how much a bare linear head can overfit on sparse fine-grained classes. ## Key points - Model: bert-base-arabic-camelbert-mix (Inoue et al., 2021), fine-tuned on Wojood-Fine (Liqreina et al., 2023) with one linear classification layer over 51 entity labels plus 'O'. - Data splits: 70% train, 10% validation, 20% test. Test labels were withheld for blind evaluation. - Hyperparameters: batch size 32, up to 50 epochs, AdamW, learning rate 1e-4, StepLR scheduler, cross-entropy loss. Early stopping halted training after 10 epochs without validation-loss improvement. - Results by split: | Split | Precision | Recall | F1 | |---|---|---|---| | Training | 95.19% | 96.57% | 95.87% | | Validation | 87.86% | 90.49% | 89.16% | | Testing | 88.06% | 84.90% | 86.45% | - Leaderboard: mucAI led Subtask-1 with F1 91, and the baseline scored 89. Bangor's 86 was the lowest of the listed entries. ## Interesting ideas - A single linear layer mapping contextual subword vectors directly to a large fine-grained label set gives a minimal, transparent tagging head that is easy to inspect and compare against richer heads. - Wordpiece tokens are aligned back to word-level labels so the subword encoder can be trained against word-level gold annotation. - Precision, recall and F1 are reported separately for train, validation and test, so the size of the generalization gap becomes a visible diagnostic rather than a hidden number. - Placing a system next to the organizers' baseline reveals that a plain fine-tune fell short, which an absolute score alone would hide. - The authors point to data sparsity in fine-grained classes as the likely source of weakness, which argues for checking per-class coverage before trusting aggregate scores. ## For Mova How these ideas could serve Mova, our small open language model — its files, stages and tests: - **I1** (tokens): A per-token linear classifier over encoder states could serve as the explainable floor for fine-grained entity or POS tagging, with any heavier tagger required to beat it. - **I2** (tree): gparse needs the same word↔subword alignment discipline to project UD heads and labels from treebank words onto transformer pieces and back without drift. - **I3** (learn): Evaluation reports should always print the train/dev/test triple, so silver-data overfitting shows up before it contaminates later stages. - **I4** (learn): Every new model should be scored against a fixed simple baseline acting as a negative control, and a gain should count only when it clears that bar. - **I5** (world): When entity types are compiled from WordNet/Wikidata into many subtypes, rare subtypes should be flagged and evaluated separately rather than averaged away. *Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.* 📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works 🧭 Topics (2): [Semitic languages](https://md.research.elamur.ai/free/en/topics/semitic-languages/) · 3,066 works · [🏷️ Named entity recognition](https://md.research.elamur.ai/free/en/topics/named-entity-recognition/) · 214 works ## Cite Cite as: Norah Alshammari. 2024. Bangor University at WojoodNER 2024: Advancing Arabic Named Entity Recognition with CAMeLBERT-Mix. Proceedings of the Second Arabic Natural Language Processing Conference. The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @inproceedings{alshammari2024bangor, title = {{Bangor University at WojoodNER 2024: Advancing Arabic Named Entity Recognition with CAMeLBERT-Mix}}, author = {Norah Alshammari}, booktitle = {Proceedings of the Second Arabic Natural Language Processing Conference}, year = {2024}, doi = {10.18653/v1/2024.arabicnlp-1.105}, url = {https://doi.org/10.18653/v1/2024.arabicnlp-1.105} } ``` - [← previous Baleegh at KSAA-CAD 2024: Towards Enhancing Arabic Reverse Dictionaries](https://md.research.elamur.ai/free/en/papers/alheraki-2024-baleegh-ksaa-cad-2024-enhancing/) - [next → Can ChatGPT capture swearing nuances? Evidence from translating Arabic oaths](https://md.research.elamur.ai/free/en/papers/shormani-2024-chatgpt-capture-swearing-nuances-evidence/) - [↑ back to papers of 2024](https://md.research.elamur.ai/free/en/papers/2024/page/14/) ## References 8 references, 5 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. Benajiba, Y., Rosso, P. and Benedíruiz, J.M., 2007. Anersys: An arabic named entity recognition system based on maximum entropy. In Computational Linguistics and Intelligent Text Processing: 8th International Conference, CICLing 2007, Mexico City, Mexico, February 18-24, 2007. Proceedings 8 (pp. 143-153). Springer Berlin Heidelberg. [find](https://scholar.google.com/scholar?q=Benajiba%2C+Y%2E%2C+Rosso%2C+P%2E+and+Bened%C3%ADruiz%2C+J%2EM%2E%2C+2007%2E+Anersys%3A+An+arabic+named+entity+recognition+system+based+on+maximum+entropy%2E+In+Computational+Linguistics+and+Intelligent+Text+Processing%3A+8th+Inter) 2. Inoue, G., Alhafni, B., Baimukan, N., Bouamor, H. and Habash, N., 2021. [The interplay of variant, size, and task type in Arabic pre-trained language models](https://md.research.elamur.ai/free/en/papers/inoue-2021-interplay-variant-size-task-type/). arXiv preprint arXiv:2103.06678. [↗](https://arxiv.org/abs/2103.06678) 3. Jarrar, M., Abdul-Mageed, M., Khalilia, M., Talafha, B., Elmadany, A., Hamad, N. and Omar, A., 2023. [WojoodNER 2023: The First Arabic Named Entity Recognition Shared Task](https://md.research.elamur.ai/free/en/papers/jarrar-2023-wojoodner-2023-first-arabic-named/). arXiv preprint arXiv:2310.16153. [↗](https://arxiv.org/abs/2310.16153) 4. Jarrar, M., Khalilia, M. and Ghanem, S., 2022. [Wojood: Nested arabic named entity corpus and recognition using bert](https://md.research.elamur.ai/free/en/papers/jarrar-2022-wojood-nested-arabic-named-entity/). arXiv preprint arXiv:2205.09651. [↗](https://arxiv.org/abs/2205.09651) 5. Jarrar, M., Hamad, N., Khalilia, M., Talafha, B., Elmadany, A. and Abdul-Mageed, M., 2024. [WojoodNER 2024: The Second Arabic Named Entity Recognition Shared Task](https://md.research.elamur.ai/free/en/papers/jarrar-2024-wojoodner-2024-second-arabic-named/). In: Proceedings of the 2nd Arabic Natural Language Processing Conference (Arabic-NLP), Part of the ACL 2024. Association for Computational Linguistics. 6. Liqreina, H., Jarrar, M., Khalilia, M., El-Shangiti, A.O. and AbdulMageed, M., 2023. [Arabic fine-grained entity recognition](https://md.research.elamur.ai/free/en/papers/liqreina-2023-arabic-fine-grained-entity-recognition/). arXiv preprint arXiv:2310.17333. [↗](https://arxiv.org/abs/2310.17333) 7. Salah, R.E. and Zakaria, L.Q.B., 2018, March. Building the classical Arabic named entity recognition corpus (CANERCorpus). In 2018 Fourth International Conference on Information Retrieval and Knowledge Management (CAMP) (pp. 1-8). IEEE. [find](https://scholar.google.com/scholar?q=Salah%2C+R%2EE%2E+and+Zakaria%2C+L%2EQ%2EB%2E%2C+2018%2C+March%2E+Building+the+classical+Arabic+named+entity+recognition+corpus+%28CANERCorpus%29%2E+In+2018+Fourth+International+Conference+on+Information+Retrieval+and+Knowledg) 8. Walker, C., Strassel, S., Medero, J. and Maeda, K., 2005. Ace 2005 multilingual training corpus-linguistic data consortium. URL: [https://catalog.ldc](https://catalog.ldc). upenn. edu/LDC2006T06. [↗](https://catalog.ldc) *Updated 31 October 2026*