---
title: "Exploring Data and Parameter Efficient — Kanjirangat 2025"
description: "The paper asks how well Arabic Dialect Identification (ADI) can be handled cheaply, either by spending little labelled data (prompting LLMs) or by…"
authors: ["Vani Kanjirangat", "Ljiljana Dolamic", "Fabio Rinaldi"]
year: 2025
venue: "arXiv:2509.13775"
source: "https://arxiv.org/abs/2509.13775"
doi: "10.48550/arxiv.2509.13775"
arxiv: "2509.13775"
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/kanjirangat-2025-exploring-data-parameter-efficient-strategies/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/kanjirangat-2025-exploring-data-parameter-efficient-strategies/)

[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/2/) / Exploring Data and Parameter Efficient Strategies for Arabic Dialect Identifications

# Exploring Data and Parameter Efficient Strategies for Arabic Dialect Identifications

**Authors:** [Vani Kanjirangat](https://md.research.elamur.ai/free/en/authors/vani-kanjirangat/), [Ljiljana Dolamic](https://md.research.elamur.ai/free/en/authors/ljiljana-dolamic/), [Fabio Rinaldi](https://md.research.elamur.ai/free/en/authors/fabio-rinaldi/) · **Year:** 2025 · **Venue:** arXiv:2509.13775 · **Licence:** [CC BY 4.0 (arXiv)](http://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/2509.13775) · [PDF](https://arxiv.org/pdf/2509.13775) · [DOI 10.48550/arxiv.2509.13775](https://doi.org/10.48550/arxiv.2509.13775) · [arXiv 2509.13775](https://arxiv.org/abs/2509.13775) · [OpenAlex](https://openalex.org/W4417080463)

**Citations:** 0 citations (openalex-snapshot · 2026-10-14) · 1 in our library, of the 140884 papers whose bibliographies we read

## Summary
The paper asks how well Arabic Dialect Identification (ADI) can be handled cheaply, either by spending little labelled data (prompting LLMs) or by updating few parameters (PEFT). The authors fine-tune five Arabic-specific BERT-style encoders on four corpora: VarDial ADI, AOC, NADI-2022 and NADI-2023. On the strongest of these encoders, MARBERTv2, they then compare full fine-tuning with LoRA and four soft-prompt methods: prefix-tuning, prompt-tuning, P-tuning and P-tuning V2. For the data-light side, they run zero-shot and few-shot hard prompts on Phi-3.5-mini and the Arabic LLM SILMA. The prompts include vanilla, chain-of-thought-style, binary and a CARP-inspired variant that feeds the model dialect keyword clues. Label output is forced through Skorch. The decoder LLMs largely fail and collapse onto one favoured dialect. Soft prompts reach reasonable scores, and LoRA does best, slightly beating full fine-tuning on the balanced 18-class NADI-2023. The study matters because it shows that fine-grained variety discrimination still needs supervised adaptation, and that low-rank tuning is enough to provide it.

## Key points
- Full fine-tuning used dropout 0.3, learning rate 1e-5, batch size 8 and 5 epochs. MARBERTv2 was strongest overall, with F of 0.84 on NADI-2023, 0.79 on AOC and 0.30 on NADI-2022. On VarDial ADI, MultiDialectBERT scored slightly higher (0.41 vs 0.40).
- Scores on the unbalanced NADI-2022 are far below those on the balanced NADI-2023, even though both cover 18 dialects with roughly 18–20k training utterances.
- On NADI-2023 with MARBERTv2:
  - LoRA (r=8) beats full fine-tuning by about 1 point.
  - P-tuning V2, which inserts prompts at every layer, reaches 83% F, about 3 points above the other soft-prompt methods.
  - Prefix-tuning, prompt-tuning and P-tuning, each with 20 virtual tokens, perform alike.
- Zero-shot Phi-3.5-mini gets only 8% F and over-predicts Egyptian. SILMA (9B, Gemma-based) over-predicts Saudi. Removing the favoured label just moves the bias to another class.
- Binary prompting helps a little. The CARP-style dialect vocabularies generated by ChatGPT acted more like noise than useful hints.

## Interesting ideas
- Constrain an LLM's answer by intercepting its logits and restricting them to the allowed label set, instead of parsing free text; this makes zero-shot classification measurable and comparable to trained classifiers. — For Mova (learn): LLM teacher tiers could be forced to choose among the legal UD labels or frame roles, so their silver annotations never contain invented categories.
- When a model collapses onto one label, delete that label and re-test; if the bias simply jumps to another class, the model has no real discriminative signal. — For Mova (learn): this is a cheap negative-control test for any witness parser or teacher that seems to over-prefer one relation or sense.
- Auto-generated "clue" lexicons from a chatbot can hurt rather than help, so machine-produced background knowledge needs checking before it is injected into a decision. — For Mova (world): verb-class or ontology entries drafted by an LLM should pass validation before entering compiled knowledge, or they may add noise to world-building.
- Few-shot examples work poorly when class names carry no semantics (a dialect tag says nothing about its cues), unlike tasks such as sentiment. — For Mova (answer): when readers are tested with few-shot prompts, label names should be meaningful, or the cues should be made explicit.
- A small low-rank adapter on a strong in-domain encoder can match or beat full fine-tuning on a fine-grained variety task. — For Mova (tree): gparse could be adapted to new English varieties or converted UD dialect treebanks with LoRA adapters instead of full retraining, which keeps the base parser intact.

*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{kanjirangat2025exploring,
  title = {{Exploring Data and Parameter Efficient Strategies for Arabic Dialect Identifications}},
  author = {Kanjirangat, Vani and Dolamic, Ljiljana and Rinaldi, Fabio},
  year = {2025},
  doi = {10.48550/arxiv.2509.13775},
  eprint = {2509.13775},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2509.13775}
}
```

- [← previous Exploring Coreference Resolution in Glosses of German Sign Language](https://md.research.elamur.ai/free/en/papers/bao-2025-exploring-coreference-resolution-glosses-german/)
- [next → Exploring the Interaction of Personality, Strategy, and Learning Environment in Achieving Success in Learning Arabic Grammar](https://md.research.elamur.ai/free/en/papers/bahy-2025-exploring-interaction-personality-strategy-learning/)
- [↑ back to papers of 2025](https://md.research.elamur.ai/free/en/papers/2025/page/2/)

## References

27 references, 12 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, Amr Keleg, AbdelRahim Elmadany, Chiyu Zhang, Injy Hamed, Walid Magdy, Houda Bouamor, and Nizar Habash. 2024. NADI 2024: The Fifth Nuanced Arabic Dialect Identification Shared Task. In Proceedings of The Second Arabic Natural Language Processing Conference (ArabicNLP 2024). [find](https://scholar.google.com/scholar?q=Muhammad+Abdul%2DMageed%2C+Amr+Keleg%2C+AbdelRahim+Elmadany%2C+Chiyu+Zhang%2C+Injy+Hamed%2C+Walid+Magdy%2C+Houda+Bouamor%2C+and+Nizar+Habash%2E+2024%2E+NADI+2024%3A+The+Fifth+Nuanced+Arabic+Dialect+Identification+Shared+Ta)
2. Muhammad Abdul-Mageed, Chiyu Zhang, Abdel-Rahim Elmadany, Houda Bouamor, and Nizar Habash. 2022. NADI 2022: The third nuanced Arabic dialect identification shared task. In Proceedings of the The Seventh Arabic Natural Language Processing Workshop (WANLP), pages 85–97, Abu Dhabi, United Arab Emirates (Hybrid). Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Muhammad+Abdul%2DMageed%2C+Chiyu+Zhang%2C+Abdel%2DRahim+Elmadany%2C+Houda+Bouamor%2C+and+Nizar+Habash%2E+2022%2E+NADI+2022%3A+The+third+nuanced+Arabic+dialect+identification+shared+task%2E+In+Proceedings+of+the+The+Seven)
3. Wissam Antoun, Fady Baly, and Hazem Hajj. Arabert: Transformer-based model for arabic language understanding. In LREC 2020 Workshop Language Resources and Evaluation Conference 11–16 May 2020, page 9. [find](https://scholar.google.com/scholar?q=Wissam+Antoun%2C+Fady+Baly%2C+and+Hazem+Hajj%2E+Arabert%3A+Transformer%2Dbased+model+for+arabic+language+understanding%2E+In+LREC+2020+Workshop+Language+Resources+and+Evaluation+Conference+11%E2%80%9316+May+2020%2C+page+9%2E) [our card](https://md.research.elamur.ai/free/en/papers/antoun-2020-arabert-transformer-based-model-arabic/)
4. Yejin Bang, Samuel Cahyawijaya, Nayeon Lee, Wenliang Dai, Dan Su, Bryan Wilie, Holy Lovenia, Ziwei Ji, Tiezheng Yu, Willy Chung, et al. 2023. A multi-task, multilingual, multimodal evaluation of chatgpt on reasoning, hallucination, and interactivity. In Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 675–718. [find](https://scholar.google.com/scholar?q=Yejin+Bang%2C+Samuel+Cahyawijaya%2C+Nayeon+Lee%2C+Wenliang+Dai%2C+Dan+Su%2C+Bryan+Wilie%2C+Holy+Lovenia%2C+Ziwei+Ji%2C+Tiezheng+Yu%2C+Willy+Chung%2C+et+al%2E+2023%2E+A+multi%2Dtask%2C+multilingual%2C+multimodal+evaluation+of+chatg)
5. Houda Bouamor, Sabit Hassan, and Nizar Habash. 2019. The madar shared task on arabic fine-grained dialect identification. In Proceedings of the Fourth Arabic Natural Language Processing Workshop, pages 199– 207. [find](https://scholar.google.com/scholar?q=Houda+Bouamor%2C+Sabit+Hassan%2C+and+Nizar+Habash%2E+2019%2E+The+madar+shared+task+on+arabic+fine%2Dgrained+dialect+identification%2E+In+Proceedings+of+the+Fourth+Arabic+Natural+Language+Processing+Workshop%2C+page) [our card](https://md.research.elamur.ai/free/en/papers/bouamor-2019-madar-shared-task-arabic-fine/)
6. Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al. 2020. Language models are few-shot learners. Advances in neural information processing systems, 33:1877–1901. [find](https://scholar.google.com/scholar?q=Tom+Brown%2C+Benjamin+Mann%2C+Nick+Ryder%2C+Melanie+Subbiah%2C+Jared+D+Kaplan%2C+Prafulla+Dhariwal%2C+Arvind+Neelakantan%2C+Pranav+Shyam%2C+Girish+Sastry%2C+Amanda+Askell%2C+et+al%2E+2020%2E+Language+models+are+few%2Dshot+lear)
7. Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen, et al. 2022. Lora: Low-rank adaptation of large language models. ICLR, 1(2):3. [find](https://scholar.google.com/scholar?q=Edward+J+Hu%2C+Yelong+Shen%2C+Phillip+Wallis%2C+Zeyuan+Allen%2DZhu%2C+Yuanzhi+Li%2C+Shean+Wang%2C+Lu+Wang%2C+Weizhu+Chen%2C+et+al%2E+2022%2E+Lora%3A+Low%2Drank+adaptation+of+large+language+models%2E+ICLR%2C+1%282%29%3A3%2E)
8. 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. [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/)
9. Md Tawkat Islam Khondaker, Abdul Waheed, Muhammad Abdul-Mageed, et al. 2023. Gptaraeval: A comprehensive evaluation of chatgpt on arabic nlp. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 220–247. [find](https://scholar.google.com/scholar?q=Md+Tawkat+Islam+Khondaker%2C+Abdul+Waheed%2C+Muhammad+Abdul%2DMageed%2C+et+al%2E+2023%2E+Gptaraeval%3A+A+comprehensive+evaluation+of+chatgpt+on+arabic+nlp%2E+In+Proceedings+of+the+2023+Conference+on+Empirical+Methods)
10. Viet Lai, Nghia Ngo, Amir Pouran Ben Veyseh, Hiéu Mãn, Franck Dernoncourt, Trung Bui, and Thien Nguyen. 2023. Chatgpt beyond english: Towards a comprehensive evaluation of large language models in multilingual learning. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 13171–13189. [find](https://scholar.google.com/scholar?q=Viet+Lai%2C+Nghia+Ngo%2C+Amir+Pouran+Ben+Veyseh%2C+Hi%C3%A9u+M%C3%A3n%2C+Franck+Dernoncourt%2C+Trung+Bui%2C+and+Thien+Nguyen%2E+2023%2E+Chatgpt+beyond+english%3A+Towards+a+comprehensive+evaluation+of+large+language+models+in+mul) [our card](https://md.research.elamur.ai/free/en/papers/lai-2023-chatgpt-beyond-english-comprehensive-evaluation/)
11. Brian Lester, Rami Al-Rfou, and Noah Constant. 2021. The power of scale for parameter-efficient prompt tuning. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 3045–3059. [find](https://scholar.google.com/scholar?q=Brian+Lester%2C+Rami+Al%2DRfou%2C+and+Noah+Constant%2E+2021%2E+The+power+of+scale+for+parameter%2Defficient+prompt+tuning%2E+In+Proceedings+of+the+2021+Conference+on+Empirical+Methods+in+Natural+Language+Processing)
12. Xiang Lisa Li and Percy Liang. 2021. Prefix-tuning: Optimizing continuous prompts for generation. 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 4582– 4597. [find](https://scholar.google.com/scholar?q=Xiang+Lisa+Li+and+Percy+Liang%2E+2021%2E+Prefix%2Dtuning%3A+Optimizing+continuous+prompts+for+generation%2E+In+Proceedings+of+the+59th+Annual+Meeting+of+the+Association+for+Computational+Linguistics+and+the+11t)
13. Vladislav Lialin, Vijeta Deshpande, and Anna Rumshisky. 2023. Scaling down to scale up: A guide to parameter-efficient fine-tuning. arXiv preprint arXiv:2303.15647. [↗](https://arxiv.org/abs/2303.15647)
14. Xiao Liu, Kaixuan Ji, Yicheng Fu, Weng Tam, Zhengxiao Du, Zhilin Yang, and Jie Tang. 2022. P-tuning: Prompt tuning can be comparable to fine-tuning across scales and tasks. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 61–68. [find](https://scholar.google.com/scholar?q=Xiao+Liu%2C+Kaixuan+Ji%2C+Yicheng+Fu%2C+Weng+Tam%2C+Zhengxiao+Du%2C+Zhilin+Yang%2C+and+Jie+Tang%2E+2022%2E+P%2Dtuning%3A+Prompt+tuning+can+be+comparable+to+fine%2Dtuning+across+scales+and+tasks%2E+In+Proceedings+of+the+60th+) [our card](https://md.research.elamur.ai/free/en/papers/liu-2022-p-tuning-prompt-tuning-can/)
15. Xiao Liu, Yanan Zheng, Zhengxiao Du, Ming Ding, Yujie Qian, Zhilin Yang, and Jie Tang. 2024. Gpt understands, too. AI Open, 5:208–215. [find](https://scholar.google.com/scholar?q=Xiao+Liu%2C+Yanan+Zheng%2C+Zhengxiao+Du%2C+Ming+Ding%2C+Yujie+Qian%2C+Zhilin+Yang%2C+and+Jie+Tang%2E+2024%2E+Gpt+understands%2C+too%2E+AI+Open%2C+5%3A208%E2%80%93215%2E)
16. Muhammad Abdul Mageed, Abdelrahim Elmadany, et al. 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. [find](https://scholar.google.com/scholar?q=Muhammad+Abdul+Mageed%2C+Abdelrahim+Elmadany%2C+et+al%2E+2021%2E+Arbert+%26+marbert%3A+Deep+bidirectional+transformers+for+arabic%2E+In+Proceedings+of+the+59th+Annual+Meeting+of+the+Association+for+Computational+Li) [our card](https://md.research.elamur.ai/free/en/papers/abdul-2021-mageed-arbert-marbert-deep-bidirectional-transformers/)
17. Abdul-Mageed Muhammad, Zhang Chiyu, Bouamor Houda, and H Nizar. 2020. Nadi 2020: The first nuanced arabic dialect identification shared task. In Proceedings of the Fifth Arabic Natural Language Processing Workshop, pages 97–110. [find](https://scholar.google.com/scholar?q=Abdul%2DMageed+Muhammad%2C+Zhang+Chiyu%2C+Bouamor+Houda%2C+and+H+Nizar%2E+2020%2E+Nadi+2020%3A+The+first+nuanced+arabic+dialect+identification+shared+task%2E+In+Proceedings+of+the+Fifth+Arabic+Natural+Language+Proces)
18. OpenAI. 2023. Chatgpt. Version: GPT-4, Mar 14. Available at [https://chat.openai.com](https://chat.openai.com). [↗](https://chat.openai.com)
19. Sinno Jialin Pan. 2020. Transfer learning. Learning, 21:1–2. [find](https://scholar.google.com/scholar?q=Sinno+Jialin+Pan%2E+2020%2E+Transfer+learning%2E+Learning%2C+21%3A1%E2%80%932%2E)
20. Nitin Rane, Saurabh Choudhary, and Jayesh Rane. 2024. Gemini versus chatgpt: applications, performance, architecture, capabilities, and implementation. Journal of Applied Artificial Intelligence, 5(1):69–93. [find](https://scholar.google.com/scholar?q=Nitin+Rane%2C+Saurabh+Choudhary%2C+and+Jayesh+Rane%2E+2024%2E+Gemini+versus+chatgpt%3A+applications%2C+performance%2C+architecture%2C+capabilities%2C+and+implementation%2E+Journal+of+Applied+Artificial+Intelligence%2C+5%281%29)
21. Xiaofei Sun, Xiaoya Li, Jiwei Li, Fei Wu, Shangwei Guo, Tianwei Zhang, and Guoyin Wang. 2023. Text classification via large language models. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 8990–9005. [find](https://scholar.google.com/scholar?q=Xiaofei+Sun%2C+Xiaoya+Li%2C+Jiwei+Li%2C+Fei+Wu%2C+Shangwei+Guo%2C+Tianwei+Zhang%2C+and+Guoyin+Wang%2E+2023%2E+Text+classification+via+large+language+models%2E+In+Findings+of+the+Association+for+Computational+Linguistic) [our card](https://md.research.elamur.ai/free/en/papers/sun-2023-text-classification-large-language-models/)
22. Bashar Talafha, Mohammad Ali, Muhy Eddin Za’ter, Haitham Seelawi, Ibraheem Tuffaha, Mostafa Samir, Wael Farhan, and Hussein Al-Natsheh. 2020. Multi-dialect arabic bert for country-level dialect identification. In Proceedings of the Fifth Arabic Natural Language Processing Workshop, pages 111–118. [find](https://scholar.google.com/scholar?q=Bashar+Talafha%2C+Mohammad+Ali%2C+Muhy+Eddin+Za%E2%80%99ter%2C+Haitham+Seelawi%2C+Ibraheem+Tuffaha%2C+Mostafa+Samir%2C+Wael+Farhan%2C+and+Hussein+Al%2DNatsheh%2E+2020%2E+Multi%2Ddialect+arabic+bert+for+country%2Dlevel+dialect+identi)
23. Zhilin Yang, Zihang Dai, Yiming Yang, Jaime Carbonell, Russ R Salakhutdinov, and Quoc V Le. 2019. Xlnet: Generalized autoregressive pretraining for language understanding. Advances in neural information processing systems, 32. [find](https://scholar.google.com/scholar?q=Zhilin+Yang%2C+Zihang+Dai%2C+Yiming+Yang%2C+Jaime+Carbonell%2C+Russ+R+Salakhutdinov%2C+and+Quoc+V+Le%2E+2019%2E+Xlnet%3A+Generalized+autoregressive+pretraining+for+language+understanding%2E+Advances+in+neural+informati) [our card](https://md.research.elamur.ai/free/en/papers/yang-2019-xlnet-generalized-autoregressive-pretraining-language/)
24. Omar Zaidan and Chris Callison-Burch. 2011. The arabic online commentary dataset: an annotated dataset of informal arabic with high dialectal content. In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, pages 37–41. [find](https://scholar.google.com/scholar?q=Omar+Zaidan+and+Chris+Callison%2DBurch%2E+2011%2E+The+arabic+online+commentary+dataset%3A+an+annotated+dataset+of+informal+arabic+with+high+dialectal+content%2E+In+Proceedings+of+the+49th+Annual+Meeting+of+the+) [our card](https://md.research.elamur.ai/free/en/papers/zaidan-2011-arabic-online-commentary-dataset-annotated/)
25. Omar F Zaidan and Chris Callison-Burch. 2014. Arabic dialect identification. Computational Linguistics, 40(1):171–202. [find](https://scholar.google.com/scholar?q=Omar+F+Zaidan+and+Chris+Callison%2DBurch%2E+2014%2E+Arabic+dialect+identification%2E+Computational+Linguistics%2C+40%281%29%3A171%E2%80%93202%2E) [our card](https://md.research.elamur.ai/free/en/papers/zaidan-2014-arabic-dialect-identification/)
26. Marcos Zampieri, Shervin Malmasi, Nikola Ljubešić, Preslav Nakov, Ahmed Ali, Jörg Tiedemann, Yves Scherrer, and Noëmi Aepli. 2017. Findings of the vardial evaluation campaign 2017. In Proceedings of the fourth workshop on NLP for similar languages, varieties and dialects. [find](https://scholar.google.com/scholar?q=Marcos+Zampieri%2C+Shervin+Malmasi%2C+Nikola+Ljube%C5%A1ic%CC%81%2C+Preslav+Nakov%2C+Ahmed+Ali%2C+J%C3%B6rg+Tiedemann%2C+Yves+Scherrer%2C+and+No%C3%ABmi+Aepli%2E+2017%2E+Findings+of+the+vardial+evaluation+campaign+2017%2E+In+Proceedings+of+) [our card](https://md.research.elamur.ai/free/en/papers/zampieri-2017-findings-vardial-evaluation-campaign/)
27. Marcos Zampieri, Shervin Malmasi, Preslav Nakov, Ahmed Ali, Suwon Shon, James Glass, Yves Scherrer, Tanja Samardžić, Nikola Ljubešić, Jörg Tiedemann, et al. 2018. Language identification and morphosyntactic tagging. the second vardial evaluation campaign. [find](https://scholar.google.com/scholar?q=Marcos+Zampieri%2C+Shervin+Malmasi%2C+Preslav+Nakov%2C+Ahmed+Ali%2C+Suwon+Shon%2C+James+Glass%2C+Yves+Scherrer%2C+Tanja+Samard%C5%BEic%CC%81%2C+Nikola+Ljube%C5%A1ic%CC%81%2C+J%C3%B6rg+Tiedemann%2C+et+al%2E+2018%2E+Language+identification+and+morphos) [our card](https://md.research.elamur.ai/free/en/papers/zampieri-2018-language-identification-morphosyntactic-tagging-second/)