---
title: "MuDRiC: Multi-Dialect Reasoning for Arabic — Elozeiri 2025"
description: "Arabic commonsense benchmarks have mostly covered Modern Standard Arabic (MSA), while everyday communication happens in regional dialects."
authors: ["Kareem Elozeiri", "Mervat Abassy", "Preslav Nakov", "Yuxia Wang"]
year: 2025
venue: "arXiv:2508.13130"
source: "https://arxiv.org/abs/2508.13130"
doi: "10.48550/arxiv.2508.13130"
arxiv: "2508.13130"
licence: "CC BY 4.0 (arXiv)"
licence_url: "http://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/elozeiri-2025-mudric-multi-dialect-reasoning-arabic/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/elozeiri-2025-mudric-multi-dialect-reasoning-arabic/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2025](https://md.research.elamur.ai/free/en/papers/2025/page/3/) / MuDRiC: Multi-Dialect Reasoning for Arabic Commonsense Validation

# MuDRiC: Multi-Dialect Reasoning for Arabic Commonsense Validation

**Authors:** [Kareem Elozeiri](https://md.research.elamur.ai/free/en/authors/kareem-elozeiri/), [Mervat Abassy](https://md.research.elamur.ai/free/en/authors/mervat-abassy/), [Preslav Nakov](https://md.research.elamur.ai/free/en/authors/preslav-nakov/), Yuxia Wang · **Year:** 2025 · **Venue:** arXiv:2508.13130 · **Licence:** [CC BY 4.0 (arXiv)](http://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/2508.13130) · [PDF](https://arxiv.org/pdf/2508.13130) · [DOI 10.48550/arxiv.2508.13130](https://doi.org/10.48550/arxiv.2508.13130) · [arXiv 2508.13130](https://arxiv.org/abs/2508.13130) · [OpenAlex](https://openalex.org/W4414528134)

**Citations:** 0 citations (openalex-snapshot · 2026-10-14)

## Summary
Arabic commonsense benchmarks have mostly covered Modern Standard Arabic (MSA), while everyday communication happens in regional dialects. MSA-trained models transfer poorly to them. The authors build MuDRiC, which they describe as the first multi-dialect Arabic commonsense validation resource.

They start from two MSA sets, ADCV and ArabicSense. Each pair of "sensible vs. nonsensical" sentences is split into single sentences with binary labels. GPT-4o then translates every item into Egyptian, Gulf, Levantine and Moroccan Arabic. Quality control has two layers: Gemini 2.5 Flash screens the translations, and native speakers fix the flagged ones.

On the modelling side, they combine a BERT-style encoder with a small Graph Convolutional Network. The GCN runs over a word co-occurrence graph whose nodes carry handcrafted surface and character features. The two vectors are merged with self-attention.

The GCN branch improves accuracy for all three backbones (AraBERTv2, CAMeLBERT-mix, MARBERTv2). However, dialect-rich pretraining matters far more than the add-on, and Moroccan remains the hardest variety.

## Key points
- **Source data:**
  - ADCV has 11,000 pairs, which become 22,000 single sentences.
  - ArabicSense has 5,650 items, which become 11,288 after deduplication.
  - Translation into four dialects yields 133,152 dialectal samples (88,000 + 45,152).
- **Quality control:**
  - Gemini flagged about 8,580 translations (5.2%).
  - Only 27% of the flagged items were truly wrong, about 1.4% of all data, and annotators corrected them.
  - A random check of 500 source labels by two annotators found no errors.
- **Training setup:**
  - Experiments use about 110K ADCV-based samples, balanced by label and dialect.
  - The data has a fixed 70/15/15 split.
  - Hyperparameters: AdamW, learning rate 2e-5, batch size 128, 3 epochs.
- **Results (average accuracy over MSA and the four dialects):**

  | Backbone | Without GCN | With GCN |
  |---|---|---|
  | MARBERTv2 | 78.16 | 79.53 |
  | CAMeLBERT-mix | 72.34 | 74.28 |
  | AraBERTv2 | 65.34 | 67.01 |

- **Moroccan is the weakest subset for every model**, e.g. 73.06 with MARBERTv2 + GCN. Domain-adversarial training is also explored, but only in an appendix.

## Interesting ideas
- **Pairwise to pointwise:** Recasting "pick the sensible one of two" items as independent yes/no plausibility judgments doubles the data and gives one format that works across sources. — For Mova (answer): Multiple-choice school test items could be split into single statements, so the reader checks each one against the text's world and must justify every verdict on its own.
- **Parallel variants of the same items:** Rendering every item in several language varieties holds the content constant, so performance gaps can be attributed to the variety alone. — For Mova (tree): Building parallel sentence sets in different English registers or spelling conventions would show exactly where the perceptron parser and gparse degrade.
- **Verifier-then-human triage:** A second LLM screens the generated data, humans inspect only the flagged part, and the share of flags that turn out to be real errors is reported. — For Mova (learn): LLM teacher tiers could use a cheap checker to route only suspicious silver trees to a stronger teacher or a human, while tracking the checker's precision as a health metric.
- **Cheap surface-feature graph beside a transformer:** A tiny GCN over a word co-occurrence window, with nodes carrying length and character-count features, gives extra robustness to spelling and morphological variation at little cost. — For Mova (tokens): The tagger and lemmatizer could use explicit character-shape features to cope with misspellings and nonstandard forms, staying inspectable instead of relying on opaque embeddings.
- **Audit the gold labels, not just the generated data:** Sampling a few hundred original labels and having two annotators re-check them guards against inheriting errors from the source datasets. — For Mova (learn): Treebank and test gold could get periodic small double-annotated audits, so evaluation numbers rest on verified ground truth.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

Fields: [Linguistics & languages](https://md.research.elamur.ai/free/en/shelves/linguistics/)

## Cite

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@misc{elozeiri2025mudric,
  title = {{MuDRiC: Multi-Dialect Reasoning for Arabic Commonsense Validation}},
  author = {Elozeiri, Kareem and Abassy, Mervat and Nakov, Preslav and Wang, Yuxia},
  year = {2025},
  doi = {10.48550/arxiv.2508.13130},
  eprint = {2508.13130},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2508.13130}
}
```

- [← previous Mubeen AI: A Specialized Arabic Language Model for Heritage Preservation and User Intent Understanding](https://md.research.elamur.ai/free/en/papers/aljafari-2025-mubeen-ai-specialized-arabic-language/)
- [next → Multi-task Learning with Active Learning for Arabic Offensive Speech Detection](https://md.research.elamur.ai/free/en/papers/alansari-2025-multi-task-learning-active-learning/)
- [↑ back to papers of 2025](https://md.research.elamur.ai/free/en/papers/2025/page/3/)

## References

36 references, 9 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Muhammad Abdul-Mageed, AbdelRahim Elmadany, and El Moatez Billah Nagoudi. 2021. ARBERT & MARBERT: Deep bidirectional transformers for Arabic. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 7088–7105, Online. Association for Computational Linguistics. [↗](https://doi.org/10.18653/v1/2021.acl-long.551) [our card](https://md.research.elamur.ai/free/en/papers/abdul-2021-mageed-arbert-marbert-deep-bidirectional-transformers/)
2. Norah Alshahrani, Saied Alshahrani, Esma Wali, and Jeanna Matthews. 2024. Arabic synonym BERT-based adversarial examples for text classification. In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: Student Research Workshop, pages 137– 147, St. Julian’s, Malta. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Norah+Alshahrani%2C+Saied+Alshahrani%2C+Esma+Wali%2C+and+Jeanna+Matthews%2E+2024%2E+Arabic+synonym+BERT%2Dbased+adversarial+examples+for+text+classification%2E+In+Proceedings+of+the+18th+Conference+of+the+European+)
3. Wissam Antoun, Fady Baly, and Hazem Hajj. 2020. AraBERT: Transformer-based model for Arabic language understanding. In Proceedings of the 4th Workshop on Open-Source Arabic Corpora and Processing Tools, with a Shared Task on Offensive Language Detection, pages 9–15, Marseille, France. European Language Resource Association. [find](https://scholar.google.com/scholar?q=Wissam+Antoun%2C+Fady+Baly%2C+and+Hazem+Hajj%2E+2020%2E+AraBERT%3A+Transformer%2Dbased+model+for+Arabic+language+understanding%2E+In+Proceedings+of+the+4th+Workshop+on+Open%2DSource+Arabic+Corpora+and+Processing+Tool) [our card](https://md.research.elamur.ai/free/en/papers/antoun-2020-arabert-transformer-based-model-arabic/)
4. Gagan Bhatia, El Moatez Billah Nagoudi, Abdellah El Mekki, Fakhraddin Alwajih, and Muhammad Abdul-Mageed. 2025. Swan and ArabicMTEB: Dialect-aware, Arabic-centric, cross-lingual, and cross-cultural embedding models and benchmarks. In Findings of the Association for Computational Linguistics: NAACL 2025, pages 4654–4670, Albuquerque, New Mexico. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Gagan+Bhatia%2C+El+Moatez+Billah+Nagoudi%2C+Abdellah+El+Mekki%2C+Fakhraddin+Alwajih%2C+and+Muhammad+Abdul%2DMageed%2E+2025%2E+Swan+and+ArabicMTEB%3A+Dialect%2Daware%2C+Arabic%2Dcentric%2C+cross%2Dlingual%2C+and+cross%2Dcultural+em)
5. Yonatan Bisk, Rowan Zellers, Ronan Le Bras, Jianfeng Gao, and Yejin Choi. 2020. PIQA: reasoning about physical commonsense in natural language. In The Thirty-Fourth AAAI Conference on Artificial Intelligence, AAAI 2020, The Thirty-Second Innovative Applications of Artificial Intelligence Conference, IAAI 2020, The Tenth AAAI Symposium on Educational Advances in Artificial Intelligence, EAAI 2020, New York, NY, USA, February 7-12, 2020, pages 7432– 7439. AAAI Press. [find](https://scholar.google.com/scholar?q=Yonatan+Bisk%2C+Rowan+Zellers%2C+Ronan+Le+Bras%2C+Jianfeng+Gao%2C+and+Yejin+Choi%2E+2020%2E+PIQA%3A+reasoning+about+physical+commonsense+in+natural+language%2E+In+The+Thirty%2DFourth+AAAI+Conference+on+Artificial+Intel) [our card](https://md.research.elamur.ai/free/en/papers/bisk-2019-piqa-reasoning-about-physical-commonsense/)
6. Ernest Davis and Gary Marcus. 2015. Commonsense reasoning and commonsense knowledge in artificial intelligence. Commun. ACM, 58(9):92–103. [find](https://scholar.google.com/scholar?q=Ernest+Davis+and+Gary+Marcus%2E+2015%2E+Commonsense+reasoning+and+commonsense+knowledge+in+artificial+intelligence%2E+Commun%2E+ACM%2C+58%289%29%3A92%E2%80%93103%2E)
7. Li Du, Xiao Ding, Kai Xiong, Ting Liu, and Bing Qin. 2022. e-CARE: a new dataset for exploring explainable causal reasoning. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 432–446, Dublin, Ireland. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Li+Du%2C+Xiao+Ding%2C+Kai+Xiong%2C+Ting+Liu%2C+and+Bing+Qin%2E+2022%2E+e%2DCARE%3A+a+new+dataset+for+exploring+explainable+causal+reasoning%2E+In+Proceedings+of+the+60th+Annual+Meeting+of+the+Association+for+Computatio)
8. Javid Ebrahimi, Hao Yang, and Wei Zhang. 2021. How does adversarial fine-tuning benefit bert? CoRR, abs/2108.13602. [↗](https://arxiv.org/abs/2108.13602)
9. Yaroslav Ganin, Evgeniya Ustinova, Hana Ajakan, Pascal Germain, Hugo Larochelle, François Laviolette, Mario Marchand, and Victor Lempitsky. 2016. Domain-adversarial training of neural networks. [find](https://scholar.google.com/scholar?q=Yaroslav+Ganin%2C+Evgeniya+Ustinova%2C+Hana+Ajakan%2C+Pascal+Germain%2C+Hugo+Larochelle%2C+Fran%C3%A7ois+Laviolette%2C+Mario+Marchand%2C+and+Victor+Lempitsky%2E+2016%2E+Domain%2Dadversarial+training+of+neural+networks%2E)
10. Sepp Hochreiter and Jürgen Schmidhuber. 1997. Long short-term memory. Neural Comput., 9(8):1735–1780. [find](https://scholar.google.com/scholar?q=Sepp+Hochreiter+and+J%C3%BCrgen+Schmidhuber%2E+1997%2E+Long+short%2Dterm+memory%2E+Neural+Comput%2E%2C+9%288%29%3A1735%E2%80%931780%2E)
11. Jena D. Hwang, Chandra Bhagavatula, Ronan Le Bras, Jeff Da, Keisuke Sakaguchi, Antoine Bosselut, and Yejin Choi. 2021. (comet-) atomic 2020: On symbolic and neural commonsense knowledge graphs. In Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI 2021, Thirty-Third Conference on Innovative Applications of Artificial Intelligence, IAAI 2021, The Eleventh Symposium on Educational Advances in Artificial Intelligence, EAAI 2021, Virtual Event, February 2-9, 2021, pages 6384–6392. AAAI Press. [find](https://scholar.google.com/scholar?q=Jena+D%2E+Hwang%2C+Chandra+Bhagavatula%2C+Ronan+Le+Bras%2C+Jeff+Da%2C+Keisuke+Sakaguchi%2C+Antoine+Bosselut%2C+and+Yejin+Choi%2E+2021%2E+%28comet%2D%29+atomic+2020%3A+On+symbolic+and+neural+commonsense+knowledge+graphs%2E+In+Thi) [our card](https://md.research.elamur.ai/free/en/papers/hwang-2020-comet-atomic-2020-symbolic-neural/)
12. Go Inoue, Bashar Alhafni, Nurpeiis Baimukan, Houda Bouamor, and Nizar Habash. 2021. The interplay of variant, size, and task type in Arabic pre-trained language models. In Proceedings of the Sixth Arabic Natural Language Processing Workshop, pages 92– 104, Kyiv, Ukraine (Virtual). Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Go+Inoue%2C+Bashar+Alhafni%2C+Nurpeiis+Baimukan%2C+Houda+Bouamor%2C+and+Nizar+Habash%2E+2021%2E+The+interplay+of+variant%2C+size%2C+and+task+type+in+Arabic+pre%2Dtrained+language+models%2E+In+Proceedings+of+the+Sixth+Ara) [our card](https://md.research.elamur.ai/free/en/papers/inoue-2021-interplay-variant-size-task-type/)
13. Mete Ismayilzada, Debjit Paul, Syrielle Montariol, Mor Geva, and Antoine Bosselut. 2023. CRoW: Benchmarking commonsense reasoning in real-world tasks. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 9785–9821, Singapore. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Mete+Ismayilzada%2C+Debjit+Paul%2C+Syrielle+Montariol%2C+Mor+Geva%2C+and+Antoine+Bosselut%2E+2023%2E+CRoW%3A+Benchmarking+commonsense+reasoning+in+real%2Dworld+tasks%2E+In+Proceedings+of+the+2023+Conference+on+Empirica)
14. Albert Q. Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de Las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lucile Saulnier, Lélio Renard Lavaud, Marie-Anne Lachaux, Pierre Stock, Teven Le Scao, Thibaut Lavril, Thomas Wang, Timothée Lacroix, and William El Sayed. 2023. Mistral 7b. CoRR, abs/2310.06825. [↗](https://arxiv.org/abs/2310.06825)
15. Zhang Jiawei, Zhang Haopeng, Xia Congying, and Sun Li. 2020. GRAPH-BERT: Only attention is needed for learning graph representations. [find](https://scholar.google.com/scholar?q=Zhang+Jiawei%2C+Zhang+Haopeng%2C+Xia+Congying%2C+and+Sun+Li%2E+2020%2E+GRAPH%2DBERT%3A+Only+attention+is+needed+for+learning+graph+representations%2E)
16. Akbar Karimi, Leonardo Rossi, and Andrea Prati. 2021. Adversarial training for aspect-based sentiment analysis with bert. In 2020 25th International Conference on Pattern Recognition (ICPR), pages 8797–8803. [find](https://scholar.google.com/scholar?q=Akbar+Karimi%2C+Leonardo+Rossi%2C+and+Andrea+Prati%2E+2021%2E+Adversarial+training+for+aspect%2Dbased+sentiment+analysis+with+bert%2E+In+2020+25th+International+Conference+on+Pattern+Recognition+%28ICPR%29%2C+pages+879)
17. M Moneb Khaled, Aghyad Al Sayadi, and Ashraf Elnagar. 2023. Commonsense validation and explanation in arabic text: A comparative study using arabic bert models. In 2023 24th International Arab Conference on Information Technology (ACIT), pages 1–6. [find](https://scholar.google.com/scholar?q=M+Moneb+Khaled%2C+Aghyad+Al+Sayadi%2C+and+Ashraf+Elnagar%2E+2023%2E+Commonsense+validation+and+explanation+in+arabic+text%3A+A+comparative+study+using+arabic+bert+models%2E+In+2023+24th+International+Arab+Confere)
18. Thomas N. Kipf and Max Welling. 2017. Semi-supervised classification with graph convolutional networks. In 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24-26, 2017, Conference Track Proceedings. OpenReview.net. [find](https://scholar.google.com/scholar?q=Thomas+N%2E+Kipf+and+Max+Welling%2E+2017%2E+Semi%2Dsupervised+classification+with+graph+convolutional+networks%2E+In+5th+International+Conference+on+Learning+Representations%2C+ICLR+2017%2C+Toulon%2C+France%2C+April+24) [our card](https://md.research.elamur.ai/free/en/papers/kipf-2016-semi-supervised-classification-graph-convolutional/)
19. Salima Lamsiyah, Kamyar Zeinalipour, Samir El amrany, Matthias Brust, Marco Maggini, Pascal Bouvry, and Christoph Schommer. 2025. ArabicSense: A benchmark for evaluating commonsense reasoning in Arabic with large language models. In Proceedings of the 4th Workshop on Arabic Corpus Linguistics (WACL-4), pages 1–11, Abu Dhabi, UAE. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Salima+Lamsiyah%2C+Kamyar+Zeinalipour%2C+Samir+El+amrany%2C+Matthias+Brust%2C+Marco+Maggini%2C+Pascal+Bouvry%2C+and+Christoph+Schommer%2E+2025%2E+ArabicSense%3A+A+benchmark+for+evaluating+commonsense+reasoning+in+Arabi)
20. Hector J. Levesque, Ernest Davis, and Leora Morgenstern. 2012. The winograd schema challenge. In Principles of Knowledge Representation and Reasoning: Proceedings of the Thirteenth International Conference, KR 2012, Rome, Italy, June 10-14, 2012. AAAI Press. [find](https://scholar.google.com/scholar?q=Hector+J%2E+Levesque%2C+Ernest+Davis%2C+and+Leora+Morgenstern%2E+2012%2E+The+winograd+schema+challenge%2E+In+Principles+of+Knowledge+Representation+and+Reasoning%3A+Proceedings+of+the+Thirteenth+International+Confe)
21. Bill Yuchen Lin, Xinyue Chen, Jamin Chen, and Xiang Ren. 2019. KagNet: Knowledge-aware graph networks for commonsense reasoning. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 2829–2839, Hong Kong, China. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Bill+Yuchen+Lin%2C+Xinyue+Chen%2C+Jamin+Chen%2C+and+Xiang+Ren%2E+2019%2E+KagNet%3A+Knowledge%2Daware+graph+networks+for+commonsense+reasoning%2E+In+Proceedings+of+the+2019+Conference+on+Empirical+Methods+in+Natural+L)
22. Bill Yuchen Lin, Wangchunshu Zhou, Ming Shen, Pei Zhou, Chandra Bhagavatula, Yejin Choi, and Xiang Ren. 2020. CommonGen: A constrained text generation challenge for generative commonsense reasoning. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 1823–1840, Online. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Bill+Yuchen+Lin%2C+Wangchunshu+Zhou%2C+Ming+Shen%2C+Pei+Zhou%2C+Chandra+Bhagavatula%2C+Yejin+Choi%2C+and+Xiang+Ren%2E+2020%2E+CommonGen%3A+A+constrained+text+generation+challenge+for+generative+commonsense+reasoning%2E+I)
23. Ilya Loshchilov and Frank Hutter. 2017. Decoupled weight decay regularization. In International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Ilya+Loshchilov+and+Frank+Hutter%2E+2017%2E+Decoupled+weight+decay+regularization%2E+In+International+Conference+on+Learning+Representations%2E)
24. OpenAI. 2024. Gpt-4o system card. abs/2410.21276. [↗](https://arxiv.org/abs/2410.21276) [our card](https://md.research.elamur.ai/free/en/papers/openai-2024-gpt-4o-system-card/)
25. CoRR, Telmo Pires, Eva Schlinger, and Dan Garrette. 2019. How multilingual is multilingual BERT? In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 4996–5001, Florence, Italy. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=CoRR%2C+Telmo+Pires%2C+Eva+Schlinger%2C+and+Dan+Garrette%2E+2019%2E+How+multilingual+is+multilingual+BERT%3F+In+Proceedings+of+the+57th+Annual+Meeting+of+the+Association+for+Computational+Linguistics%2C+pages+4996%E2%80%93) [our card](https://md.research.elamur.ai/free/en/papers/pires-2019-how-multilingual-is-multilingual-bert/)
26. Abdelrahman Sadallah, Junior Cedric Tonga, Khalid Almubarak, Saeed Almheiri, Farah Atif, Chatrine Qwaider, Karima Kadaoui, Sara Shatnawi, Yaser Alesh, and Fajri Koto. 2025. Commonsense reasoning in Arab culture. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 7695– 7710, Vienna, Austria. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Abdelrahman+Sadallah%2C+Junior+Cedric+Tonga%2C+Khalid+Almubarak%2C+Saeed+Almheiri%2C+Farah+Atif%2C+Chatrine+Qwaider%2C+Karima+Kadaoui%2C+Sara+Shatnawi%2C+Yaser+Alesh%2C+and+Fajri+Koto%2E+2025%2E+Commonsense+reasoning+in+Ar)
27. Maarten Sap, Ronan Le Bras, Emily Allaway, Chandra Bhagavatula, Nicholas Lourie, Hannah Rashkin, Brendan Roof, Noah A. Smith, and Yejin Choi. 2019a. Atomic: an atlas of machine commonsense for if-then reasoning. In Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence and Thirty-First Innovative Applications of Artificial Intelligence Conference and Ninth AAAI Symposium on Educational Advances in Artificial Intelligence, AAAI’19/IAAI’19/EAAI’19. AAAI Press. [find](https://scholar.google.com/scholar?q=Maarten+Sap%2C+Ronan+Le+Bras%2C+Emily+Allaway%2C+Chandra+Bhagavatula%2C+Nicholas+Lourie%2C+Hannah+Rashkin%2C+Brendan+Roof%2C+Noah+A%2E+Smith%2C+and+Yejin+Choi%2E+2019a%2E+Atomic%3A+an+atlas+of+machine+commonsense+for+if%2Dthen)
28. Maarten Sap, Hannah Rashkin, Derek Chen, Ronan Le Bras, and Yejin Choi. 2019b. Social IQa: Commonsense reasoning about social interactions. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 4463– 4473, Hong Kong, China. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Maarten+Sap%2C+Hannah+Rashkin%2C+Derek+Chen%2C+Ronan+Le+Bras%2C+and+Yejin+Choi%2E+2019b%2E+Social+IQa%3A+Commonsense+reasoning+about+social+interactions%2E+In+Proceedings+of+the+2019+Conference+on+Empirical+Methods+i)
29. Maarten Sap, Vered Shwartz, Antoine Bosselut, Yejin Choi, and Dan Roth. 2020. Commonsense reasoning for natural language processing. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: Tutorial Abstracts, pages 27–33, Online. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Maarten+Sap%2C+Vered+Shwartz%2C+Antoine+Bosselut%2C+Yejin+Choi%2C+and+Dan+Roth%2E+2020%2E+Commonsense+reasoning+for+natural+language+processing%2E+In+Proceedings+of+the+58th+Annual+Meeting+of+the+Association+for+Co)
30. Franco Scarselli, Marco Gori, Ah Chung Tsoi, Markus Hagenbuchner, and Gabriele Monfardini. 2009. The graph neural network model. IEEE Transactions on Neural Networks, 20(1):61–80. [find](https://scholar.google.com/scholar?q=Franco+Scarselli%2C+Marco+Gori%2C+Ah+Chung+Tsoi%2C+Markus+Hagenbuchner%2C+and+Gabriele+Monfardini%2E+2009%2E+The+graph+neural+network+model%2E+IEEE+Transactions+on+Neural+Networks%2C+20%281%29%3A61%E2%80%9380%2E)
31. Sanad Sha’ban and Nizar Habash. 2025. The Arabic generality score: Another dimension of modeling Arabic dialectness. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 29990–30001, Suzhou, China. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Sanad+Sha%E2%80%99ban+and+Nizar+Habash%2E+2025%2E+The+Arabic+generality+score%3A+Another+dimension+of+modeling+Arabic+dialectness%2E+In+Proceedings+of+the+2025+Conference+on+Empirical+Methods+in+Natural+Language+Proc)
32. Alon Talmor, Jonathan Herzig, Nicholas Lourie, and Jonathan Berant. 2019. CommonsenseQA: A question answering challenge targeting commonsense knowledge. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 4149–4158, Minneapolis, Minnesota. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Alon+Talmor%2C+Jonathan+Herzig%2C+Nicholas+Lourie%2C+and+Jonathan+Berant%2E+2019%2E+CommonsenseQA%3A+A+question+answering+challenge+targeting+commonsense+knowledge%2E+In+Proceedings+of+the+2019+Conference+of+the+No)
33. Saja Khaled Tawalbeh and Mohammad Al-Smadi. 2020. Is this sentence valid? an arabic dataset for commonsense validation. CoRR, abs/2008.10873. [↗](https://arxiv.org/abs/2008.10873) [our card](https://md.research.elamur.ai/free/en/papers/tawalbeh-2020-this-sentence-valid-arabic-dataset/)
34. Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timothée Lacroix, Baptiste Rozière, Naman Goyal, Eric Hambro, Faisal Azhar, Aurélien Rodriguez, Armand Joulin, Edouard Grave, and Guillaume Lample. 2023. Llama: Open and efficient foundation language models. CoRR, abs/2302.13971. [↗](https://arxiv.org/abs/2302.13971)
35. Cunxiang Wang, Shuailong Liang, Yili Jin, Yilong Wang, Xiaodan Zhu, and Yue Zhang. 2020. SemEval-2020 task 4: Commonsense validation and explanation. In Proceedings of the Fourteenth Workshop on Semantic Evaluation, pages 307–321, Barcelona (online). International Committee for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Cunxiang+Wang%2C+Shuailong+Liang%2C+Yili+Jin%2C+Yilong+Wang%2C+Xiaodan+Zhu%2C+and+Yue+Zhang%2E+2020%2E+SemEval%2D2020+task+4%3A+Commonsense+validation+and+explanation%2E+In+Proceedings+of+the+Fourteenth+Workshop+on+Seman)
36. Lu Zhibin, Du Pan, and Nie Jian-Yun. 2020. VGCN-BERT: Augmenting BERT with graph embedding for text classification. In Proceedings of the 42nd European Conference on Information Retrieval (ECIR 2020), pages 369–382, Lisbon, Portugal (Online). European Conference on Information Retrieval, Springer. [find](https://scholar.google.com/scholar?q=Lu+Zhibin%2C+Du+Pan%2C+and+Nie+Jian%2DYun%2E+2020%2E+VGCN%2DBERT%3A+Augmenting+BERT+with+graph+embedding+for+text+classification%2E+In+Proceedings+of+the+42nd+European+Conference+on+Information+Retrieval+%28ECIR+2020%29%2C)