---
title: "Add Noise, Tasks, or Layers? MaiNLP at the VarDial 2025"
description: "The paper describes the MaiNLP team's entry to the VarDial 2025 NorSID shared… 97.64% accuracy. 41 references, cited by 3 papers here."
authors: ["Verena Blaschke", "Felicia Körner", "Barbara Plank"]
year: 2025
venue: "Proceedings of the 12th Workshop on NLP for Similar Languages, Varieties and Dialects"
source: "https://aclanthology.org/2025.vardial-1.14/"
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/blaschke-2025-add-noise-tasks-or-layers/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/blaschke-2025-add-noise-tasks-or-layers/)

[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/12/) / Add Noise, Tasks, or Layers? MaiNLP at the VarDial 2025 Shared Task on Norwegian Dialectal Slot and Intent Detection

# Add Noise, Tasks, or Layers? MaiNLP at the VarDial 2025 Shared Task on Norwegian Dialectal Slot and Intent Detection

**Authors:** [Verena Blaschke](https://md.research.elamur.ai/free/en/authors/verena-blaschke/), [Felicia Körner](https://md.research.elamur.ai/free/en/authors/felicia-korner/) and [Barbara Plank](https://md.research.elamur.ai/free/en/authors/barbara-plank/) · **Year:** 2025 · **Venue:** [Proceedings of the 12th Workshop on NLP for Similar Languages, Varieties and Dialects](https://md.research.elamur.ai/free/en/venues/vardial/) ([VarDial 2025](https://md.research.elamur.ai/free/en/venues/vardial/2025/)) · **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/2025.vardial-1.14/) · [PDF](https://aclanthology.org/2025.vardial-1.14.pdf) · [OpenAlex](https://openalex.org/W4406192838)

**Citations:** 0 citations (OpenAlex, 2026-10-14) · [3](https://md.research.elamur.ai/free/en/papers/blaschke-2025-add-noise-tasks-or-layers/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
The paper describes the MaiNLP team's entry to the VarDial 2025 NorSID shared task: slot and intent detection (SID) for Bokmål and three Norwegian dialect groups (North Norwegian, Trønder, West Norwegian). The authors note that many low-resource techniques have never been compared on the same dialectal SID data, so they test several on one benchmark.

They fine-tune NorBERT v3, ScandiBERT and mDeBERTa v3 with MaChAmp, using a CRF for slots. Each model is trained on one of three sources: gold English xSID, a machine-translated Bokmål version, or a 90:10 split of the small dialectal NoMusic development set. On top of these baselines they try:
- injecting character-level noise into the Norwegian data;
- adding auxiliary tasks, either jointly or as intermediate-task training;
- Layer Swapping, which assembles a new model from layers of separately fine-tuned "experts."

Noise injection gave the strongest intent classifier. Auxiliary tasks helped in some settings and hurt in others. A swapped model combining an English-trained expert and a dialect-trained expert produced the most robust slot predictions. This suggests cheap, modular adaptation to new varieties is feasible.

## Key points
- **Data:** xSID 0.6 (43k English training sentences plus an MT Bokmål copy with automatically projected slots) and NoMusic dialect translations of the dev/test utterances. Intents are scored by accuracy; slots by strict span F1 in the BIO scheme.
- **Noise injection:** 10, 20 or 30% of alphabetic words received a random character deletion and/or insertion. The submitted intent model, mDeBERTa with 20% noise, reached 97.64% accuracy (5th place).
- **Auxiliary tasks:** dialect identification, POS tagging and dependency parsing on the retired UD Nynorsk LIA treebank (2.3k train / 622 dev dialect sentences, with respelled phonetic transcripts), and NER on NorNE. No single task helped consistently.
- **Layer Swapping:** originally shown on a 32-layer decoder, here adapted to a 12-layer encoder via JointBERT. It ranked 3rd for slots (85.57% F1), beating the dev-trained baseline (83.68%) and the dependency-parsing intermediate model (82.57%) on three of four varieties.
- **Trade-off:** Norwegian MT data gave the best intents, while gold English or dialect data gave the best slots. The authors blame the low-quality projected slot labels in the MT data.

## Interesting ideas
- Adding random character edits to standard-language training text makes a model tolerant of spelling variants that shift subword tokenization.
- A model can be built by taking some layers from a task expert trained on lots of data and others from an expert trained on a little in-domain data; the mix seemed to regularize the dialect expert and reduce its overfitting.
- The same auxiliary task can help one subtask and hurt another, so the paper compares joint multi-task learning against intermediate-task training for each subtask separately.
- The authors trace the slot-quality gap to labels projected through machine translation, which looked plentiful but were noisy compared with small gold sets.
- Their decoders cannot emit an I- tag never seen in training, even when the matching B- tag is known, which is a hidden failure mode when span lengths differ across varieties.

## For Mova

How these ideas could serve Mova, our small open language model — its files, stages and tests:

- **I1** (tokens): Train the tagger and lemmatizer on lightly noised text so that informal or nonstandard English spellings in fables and student answers degrade gracefully.
- **I2** (tree): gparse could keep a base parser trained on a large treebank and swap in a few layers tuned on a small register-specific (dialect-converted) treebank, instead of retraining the whole model.
- **I3** (learn): When adding auxiliary objectives (e.g., POS or NER) to train a component, measure the effect per downstream stage rather than assuming a shared benefit, and keep the variant only where it actually helps.
- **I4** (learn): Silver data from translation or projection should be checked against a small gold set per label type before it enters training, since span-level labels seem most fragile.
- **I5** (frames): Make sure span or role labelers can build spans compositionally (any B with continuation), so argument spans longer than those in training data are not silently truncated.

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

## Institutions

- [Ludwig-Maximilians-Universität München](https://md.research.elamur.ai/free/en/universities/ludwig-maximilians-universitat-munchen/) — University, Munich, Germany · 107 works · 56,478 citations
- [Munich Center for Machine Learning](https://md.research.elamur.ai/free/en/universities/munich-center-for-machine-learning/) — University, Munich, Germany · 57 works · 1,094 citations

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works

## Cite

Cite as: Verena Blaschke, Felicia Körner and Barbara Plank. 2025. Add Noise, Tasks, or Layers? MaiNLP at the VarDial 2025 Shared Task on Norwegian Dialectal Slot and Intent Detection. Proceedings of the 12th Workshop on NLP for Similar Languages, Varieties and Dialects.

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

```bibtex
@inproceedings{blaschke2025add,
  title = {{Add Noise, Tasks, or Layers? MaiNLP at the VarDial 2025 Shared Task on Norwegian Dialectal Slot and Intent Detection}},
  author = {Verena Blaschke, Felicia Körner and Barbara Plank},
  booktitle = {Proceedings of the 12th Workshop on NLP for Similar Languages, Varieties and Dialects},
  year = {2025},
  url = {https://aclanthology.org/2025.vardial-1.14/}
}
```

- [← previous Adapting Psycholinguistic Research for LLMs: Gender-inclusive Language in a Coreference Context](https://md.research.elamur.ai/free/en/papers/bartl-2025-adapting-psycholinguistic-research-llms-gender/)
- [next → Advancing African-Accented English Speech Recognition: Epistemic Uncertainty-Driven Data Selection for Generalizable ASR Models](https://md.research.elamur.ai/free/en/papers/dossou-2025-advancing-african-accented-english-speech/)
- [↑ back to papers of 2025](https://md.research.elamur.ai/free/en/papers/2025/page/12/)

## References

41 references, 17 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Qian Chen, Zhu Zhuo, and Wen Wang. 2019. BERT for joint intent classification and slot filling. Preprint, arXiv:1902.10909. [↗](https://arxiv.org/abs/1902.10909)
2. Noëmi Aepli, Çağrı Çöltekin, Rob Van Der Goot, Tommi Jauhiainen, Mourhaf Kazzaz, Nikola Ljubešić, Kai North, Barbara Plank, Yves Scherrer, and Marcos Zampieri. 2023. Findings of the VarDial evaluation campaign 2023. In Tenth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial 2023), pages 251–261, Dubrovnik, Croatia. Association for Computational Linguistics. [↗](https://doi.org/10.48550/arxiv.2305.20080)
3. Noëmi Aepli and Rico Sennrich. 2022. Improving zero-shot cross-lingual transfer between closely related languages by injecting character-level noise. In Findings of the Association for Computational Linguistics: ACL 2022, pages 4074–4083, Dublin, Ireland. Association for Computational Linguistics. [↗](https://doi.org/10.48448/8swj-r062)
4. Ekaterina Artemova, Verena Blaschke, and Barbara Plank. 2024. Exploring the robustness of task-oriented dialogue systems for colloquial German varieties. In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 445–468, St. Julian’s, Malta. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Ekaterina+Artemova%2C+Verena+Blaschke%2C+and+Barbara+Plank%2E+2024%2E+Exploring+the+robustness+of+task%2Doriented+dialogue+systems+for+colloquial+German+varieties%2E+In+Proceedings+of+the+18th+Conference+of+the+E)
5. Lucas Bandarkar, Benjamin Muller, Pritish Yuvraj, Rui Hou, Nayan Singhal, Hongjiang Lv, and Bing Liu. 2024. Layer swapping for zero-shot cross-lingual transfer in large language models. Preprint, arXiv:2410.01335. [↗](https://arxiv.org/abs/2410.01335)
6. Verena Blaschke, Barbara Kovačić, Siyao Peng, Hinrich Schütze, and Barbara Plank. 2024. MaiBaam: A multi-dialectal Bavarian Universal Dependency treebank. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 10921–10938, Torino, Italia. ELRA and ICCL. [find](https://scholar.google.com/scholar?q=Verena+Blaschke%2C+Barbara+Kovac%CC%8Cic%CC%81%2C+Siyao+Peng%2C+Hinrich+Sch%C3%BCtze%2C+and+Barbara+Plank%2E+2024%2E+MaiBaam%3A+A+multi%2Ddialectal+Bavarian+Universal+Dependency+treebank%2E+In+Proceedings+of+the+2024+Joint+Internatio)
7. Verena Blaschke, Hinrich Schütze, and Barbara Plank. 2023. Does manipulating tokenization aid cross-lingual transfer? a study on POS tagging for non-standardized languages. In Tenth Workshop on NLP Alexis Conneau, Kartikay Khandelwal, Naman Goyal, Vishrav Chaudhary, Guillaume Wenzek, Francisco Guzmán, Edouard Grave, Myle Ott, Luke Zettlemoyer, and Veselin Stoyanov. 2020. Unsupervised cross-lingual representation learning at scale. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 8440– 8451, Online. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Verena+Blaschke%2C+Hinrich+Sch%C3%BCtze%2C+and+Barbara+Plank%2E+2023%2E+Does+manipulating+tokenization+aid+cross%2Dlingual+transfer%3F+a+study+on+POS+tagging+for+non%2Dstandardized+languages%2E+In+Tenth+Workshop+on+NLP+Al)
8. Alice Coucke, Alaa Saade, Adrien Ball, Théodore Bluche, Alexandre Caulier, David Leroy, Clément Doumouro, Thibault Gisselbrecht, Francesco Caltagirone, Thibaut Lavril, Maël Primet, and Joseph Dureau. 2018. [Snips voice platform: An embedded spoken language understanding system for private-by-design voice interfaces](https://md.research.elamur.ai/free/en/papers/coucke-2018-snips-voice-platform-embedded-spoken/). Preprint, arXiv:1805.10190. [↗](https://arxiv.org/abs/1805.10190)
9. Marie-Catherine de Marneffe, Christopher D. Manning, Joakim Nivre, and Daniel Zeman. 2021. [Universal Dependencies](https://md.research.elamur.ai/free/en/papers/marneffe-2021-universal-dependencies-2/). Computational Linguistics, 47(2):255–308.
10. Hossam Elkordi, Ahmed Sakr, Marwan Torki, and Nagwa El-Makky. 2024. [AlexuNLP24 at AraFinNLP2024: Multi-dialect Arabic intent detection with contrastive learning in banking domain](https://md.research.elamur.ai/free/en/papers/elkordi-2024-alexunlp24-arafinnlp2024-multi-dialect-arabic/). In Proceedings of The Second Arabic Natural Language Processing Conference, pages 415–421, Bangkok, Thailand. Association for Computational Linguistics. [↗](https://doi.org/10.13140/rg.2.2.14741.74729)
11. Murhaf Fares and Samia Touileb. 2024. [BabelBot at AraFinNLP2024: Fine-tuning t5 for multi-dialect intent detection with synthetic data and model ensembling](https://md.research.elamur.ai/free/en/papers/fares-2024-babelbot-arafinnlp2024-fine-tuning-t5/). In Proceedings of The Second Arabic Natural Language Processing Conference, pages 433–440, Bangkok, Thailand. Association for Computational Linguistics. [↗](https://doi.org/10.48448/x10m-e229)
12. Jack FitzGerald, Christopher Hench, Charith Peris, Scott Mackie, Kay Rottmann, Ana Sanchez, Aaron Nash, Liam Urbach, Vishesh Kakarala, Richa Singh, Swetha Ranganath, Laurie Crist, Misha Britan, Wouter Leeuwis, Gokhan Tur, and Prem Natarajan. 2023. MASSIVE: A 1M-example multilingual natural language understanding dataset with 51 typologically-diverse languages. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 4277–4302, Toronto, Canada. Association for Computational Linguistics. Aaron Grattafiori, Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Alex Vaughan, Amy Yang, Angela Fan, Anirudh Goyal, Anthony Hartshorn, Aobo Yang, Archi Mitra, Archie Sravankumar, Artem Korenev, Arthur Hinsvark, Arun Rao, Aston Zhang, Aurelien Rodriguez, Austen Gregerson, Ava Spataru, Baptiste Roziere, Bethany Biron, Binh Tang, Bobbie Chern, Charlotte Caucheteux, Chaya Nayak, Chloe Bi, Chris Marra, Chris McConnell, Christian Keller, Christophe Touret, Chunyang Wu, Corinne Wong, Cristian Canton Ferrer, Cyrus Nikolaidis, Damien Allonsius, Daniel Song, Danielle Pintz, Danny Livshits, Danny Wyatt, David Esiobu, Dhruv Choudhary, Dhruv Mahajan, Diego Garcia-Olano, Diego Perino, Dieuwke Hupkes, Egor Lakomkin, Ehab AlBadawy, Elina Lobanova, Emily Dinan, Eric Michael Smith, Filip Radenovic, Francisco Guzmán, Frank Zhang, Gabriel Synnaeve, Gabrielle Lee, Georgia Lewis Anderson, Govind Thattai, Graeme Nail, Gregoire Mialon, Guan Pang, Guillem Cucurell, Hailey Nguyen, Hannah Korevaar, Hu Xu, Hugo Touvron, Iliyan Zarov, Imanol Arrieta Ibarra, Isabel Kloumann, Ishan Misra, Ivan Evtimov, Jack Zhang, Jade Copet, Jaewon Lee, Jan Geffert, Jana Vranes, Jason Park, Jay Mahadeokar, Jeet Shah, Jelmer van der Linde, Jennifer Billock, Jenny Hong, Jenya Lee, Jeremy Fu, Jianfeng Chi, Jianyu Huang, Jiawen Liu, Jie Wang, Jiecao Yu, Joanna Bitton, Joe Spisak, Jongsoo Park, Joseph Rocca, Joshua Johnstun, Joshua Saxe, Junteng Jia, Kalyan Vasuden Alwala, Karthik Prasad, Kartikeya Upasani, Kate Plawiak, Ke Li, Kenneth Heafield, Kevin Stone, Khalid El-Arini, Krithika Iyer, Kshitiz Malik, Kuenley Chiu, Kunal Bhalla, Kushal Lakhotia, Lauren Rantala-Yeary, Laurens van der Maaten, Lawrence Chen, Liang Tan, Liz Jenkins, Louis Martin, Lovish Madaan, Lubo Malo, Lukas Blecher, Lukas Landzaat, Luke de Oliveira, Madeline Muzzi, Mahesh Pasupuleti, Mannat Singh, Manohar Paluri, Marcin Kardas, Maria Tsimpoukelli, Mathew Oldham, Mathieu Rita, Maya Pavlova, Melanie Kambadur, Mike Lewis, Min Si, Mitesh Kumar Singh, Mona Hassan, Naman Goyal, Narjes Torabi, Nikolay Bashlykov, Nikolay Bogoychev, Niladri Chatterji, Ning Zhang, Olivier Duchenne, Onur Çelebi, Patrick Alrassy, Pengchuan Zhang, Pengwei Li, Petar Vasic, Peter Weng, Prajjwal Bhargava, Pratik Dubal, Praveen Krishnan, Punit Singh Koura, Puxin Xu, Qing He, Qingxiao Dong, Ragavan Srinivasan, Raj Ganapathy, Ramon Calderer, Ricardo Silveira Cabral, Robert Stojnic, Roberta Raileanu, Rohan Maheswari, Rohit Girdhar, Rohit Patel, Romain Sauvestre, Ronnie Polidoro, Roshan Sumbaly, Ross Taylor, Ruan Silva, Rui Hou, Rui Wang, Saghar Hosseini, Sahana Chennabasappa, Sanjay Singh, Sean Bell, Seohyun Sonia Kim, Sergey Edunov, Shaoliang Nie, Sharan Narang, Sharath Raparthy, Sheng Shen, Shengye Wan, Shruti Bhosale, Shun Zhang, Simon Vandenhende, Soumya Batra, Spencer Whitman, Sten Sootla, Stephane Collot, Suchin Gururangan, Sydney Borodinsky, Tamar Herman, Tara Fowler, Tarek Sheasha, Thomas Georgiou, Thomas Scialom, Tobias Speckbacher, Todor Mihaylov, Tong Xiao, Ujjwal Karn, Vedanuj Goswami, Vibhor Gupta, Vignesh Ramanathan, Viktor Kerkez, Vincent Gonguet, Virginie Do, Vish Vogeti, Vítor Albiero, Vladan Petrovic, Weiwei Chu, Wenhan Xiong, Wenyin Fu, Whitney Meers, Xavier Martinet, Xiaodong Wang, Xiaofang Wang, Xiaoqing Ellen Tan, Xide Xia, Xinfeng Xie, Xuchao Jia, Xuewei Wang, Yaelle Goldschlag, Yashesh Gaur, Yasmine Babaei, Yi Wen, Yiwen Song, Yuchen Zhang, Yue Li, Yuning Mao, Zacharie Delpierre Coudert, Zheng Yan, Zhengxing Chen, Zoe Papakipos, Aaditya Singh, Aayushi Srivastava, Abha Jain, Adam Kelsey, Adam Shajnfeld, Adithya Gangidi, Adolfo Victoria, Ahuva Goldstand, Ajay Menon, Ajay Sharma, Alex Boesenberg, Alexei Baevski, Allie Feinstein, Amanda Kallet, Amit Sangani, Amos Teo, Anam Yunus, Andrei Lupu, Andres Alvarado, Andrew Caples, Andrew Gu, Andrew Ho, Andrew Poulton, Andrew Ryan, Ankit Ramchandani, Annie Dong, Annie Franco, Anuj Goyal, Aparajita Saraf, Arkabandhu Chowdhury, Ashley Gabriel, Ashwin Bharambe, Assaf Eisenman, Azadeh Yazdan, Beau James, Ben Maurer, Benjamin Leonhardi, Bernie Huang, Beth Loyd, Beto De Paola, Bhargavi Paranjape, Bing Liu, Bo Wu, Boyu Ni, Braden Hancock, Bram Wasti, Brandon Spence, Brani Stojkovic, Brian Gamido, Britt Montalvo, Carl Parker, Carly Burton, Catalina Mejia, Ce Liu, Changhan Wang, Changkyu Kim, Chao Zhou, Chester Hu, Ching-Hsiang Chu, Chris Cai, Chris Tindal, Christoph Feichtenhofer, Cynthia Gao, Damon Civin, Dana Beaty, Daniel Kreymer, Daniel Li, David Adkins, David Xu, Davide Testuggine, Delia David, Devi Parikh, Diana Liskovich, Didem Foss, Dingkang Wang, Duc Le, Dustin Holland, Edward Dowling, Eissa Jamil, Elaine Montgomery, Eleonora Presani, Emily Hahn, Emily Wood, Eric-Tuan Le, Erik Brinkman, Esteban Arcaute, Evan Dunbar, Evan Smothers, Fei Sun, Felix Kreuk, Feng Tian, Filippos Kokkinos, Firat Ozgenel, Francesco Caggioni, Frank Kanayet, Frank Seide, Gabriela Medina Florez, Gabriella Schwarz, Gada Badeer, Georgia Swee, Gil Halpern, Grant Herman, Grigory Sizov, Guangyi, Zhang, Guna Lakshminarayanan, Hakan Inan, Hamid Shojanazeri, Han Zou, Hannah Wang, Hanwen Zha, Haroun Habeeb, Harrison Rudolph, Helen Suk, Henry Aspegren, Hunter Goldman, Hongyuan Zhan, Ibrahim Damlaj, Igor Molybog, Igor Tufanov, Ilias Leontiadis, Irina-Elena Veliche, Itai Gat, Jake Weissman, James Geboski, James Kohli, Janice Lam, Japhet Asher, Jean-Baptiste Gaya, Jeff Marcus, Jeff Tang, Jennifer Chan, Jenny Zhen, Jeremy Reizenstein, Jeremy Teboul, Jessica Zhong, Jian Jin, Jingyi Yang, Joe Cummings, Jon Carvill, Jon Shepard, Jonathan Mc-Phie, Jonathan Torres, Josh Ginsburg, Junjie Wang, Kai Wu, Kam Hou U, Karan Saxena, Kartikay Khandelwal, Katayoun Zand, Kathy Matosich, Kaushik Veeraraghavan, Kelly Michelena, Keqian Li, Kiran Jagadeesh, Kun Huang, Kunal Chawla, Kyle Huang, Lailin Chen, Lakshya Garg, Lavender A, Leandro Silva, Lee Bell, Lei Zhang, Liangpeng Guo, Licheng Yu, Liron Moshkovich, Luca Wehrstedt, Madian Khabsa, Manav Avalani, Manish Bhatt, Martynas Mankus, Matan Hasson, Matthew Lennie, Matthias Reso, Maxim Groshev, Maxim Naumov, Maya Lathi, Meghan Keneally, Miao Liu, Michael L. Seltzer, Michal Valko, Michelle Restrepo, Mihir Patel, Mik Vyatskov, Mikayel Samvelyan, Mike Clark, Mike Macey, Mike Wang, Miquel Jubert Hermoso, Mo Metanat, Mohammad Rastegari, Munish Bansal, Nandhini Santhanam, Natascha Parks, Natasha White, Navyata Bawa, Nayan Singhal, Nick Egebo, Nicolas Usunier, Nikhil Mehta, Nikolay Pavlovich Laptev, Ning Dong, Norman Cheng, Oleg Chernoguz, Olivia Hart, Omkar Salpekar, Ozlem Kalinli, Parkin Kent, Parth Parekh, Paul Saab, Pavan Balaji, Pedro Rittner, Philip Bontrager, Pierre Roux, Piotr Dollar, Polina Zvyagina, Prashant Ratanchandani, Pritish Yuvraj, Qian Liang, Rachad Alao, Rachel Rodriguez, Rafi Ayub, Raghotham Murthy, Raghu Nayani, Rahul Mitra, Rangaprabhu Parthasarathy, Raymond Li, Rebekkah Hogan, Robin Battey, Rocky Wang, Russ Howes, Ruty Rinott, Sachin Mehta, Sachin Siby, Sai Jayesh Bondu, Samyak Datta, Sara Chugh, Sara Hunt, Sargun Dhillon, Sasha Sidorov, Satadru Pan, Saurabh Mahajan, Saurabh Verma, Seiji Yamamoto, Sharadh Ramaswamy, Shaun Lindsay, Shaun Lindsay, Sheng Feng, Shenghao Lin, Shengxin Cindy Zha, Shishir Patil, Shiva Shankar, Shuqiang Zhang, Shuqiang Zhang, Sinong Wang, Sneha Agarwal, Soji Sajuyigbe, Soumith Chintala, Stephanie Max, Stephen Chen, Steve Kehoe, Steve Satterfield, Sudarshan Govindaprasad, Sumit Gupta, Summer Deng, Sungmin Cho, Sunny Virk, Suraj Subramanian, Sy Choudhury, Sydney Goldman, Tal Remez, Tamar Glaser, Tamara Best, Thilo Koehler, Thomas Robinson, Tianhe Li, Tianjun Zhang, Tim Matthews, Timothy Chou, Tzook Shaked, Varun Vontimitta, Victoria Ajayi, Victoria Montanez, Vijai Mohan, Vinay Satish Kumar, Vishal Mangla, Vlad Ionescu, Vlad Poenaru, Vlad Tiberiu Mihailescu, Vladimir Ivanov, Wei Li, Wenchen Wang, Wenwen Jiang, Wes Bouaziz, Will Constable, Xiaocheng Tang, Xiaojian Wu, Xiaolan Wang, Xilun Wu, Xinbo Gao, Yaniv Kleinman, Yanjun Chen, Ye Hu, Ye Jia, Ye Qi, Yenda Li, Yilin Zhang, Ying Zhang, Yossi Adi, Youngjin Nam, Yu, Wang, Yu Zhao, Yuchen Hao, Yundi Qian, Yunlu Li, Yuzi He, Zach Rait, Zachary DeVito, Zef Rosnbrick, Zhaoduo Wen, Zhenyu Yang, Zhiwei Zhao, and Zhiyu Ma. 2024. [The llama 3 herd of models](https://md.research.elamur.ai/free/en/papers/grattafiori-2024-llama-3-herd-models/). Preprint, arXiv:2407.21783. [↗](https://arxiv.org/abs/2407.21783)
13. Kristin Hagen, Live Håberg, Eirik Olsen, and Åshild Søfteland. 2018. Transkripsjonsrettleiing for LIA. [find](https://scholar.google.com/scholar?q=Kristin+Hagen%2C+Live+H%C3%A5berg%2C+Eirik+Olsen%2C+and+%C3%85shild+S%C3%B8fteland%2E+2018%2E+Transkripsjonsrettleiing+for+LIA%2E)
14. Pengcheng He, Jianfeng Gao, and Weizhu Chen. 2023. [DeBERTaV3: Improving DeBERTa using ELECTRA-style pre-training with gradient-disentangled embedding sharing](https://md.research.elamur.ai/free/en/papers/he-2021-debertav3-improving-deberta-using-electra/). In Proceedings of the Eleventh International Conference on Learning Representations (ICLR).
15. Pengcheng He, Xiaodong Liu, Jianfeng Gao, and Weizhu Chen. 2021. [DeBERTa: Decoding-enhanced BERT with disentangled attention](https://md.research.elamur.ai/free/en/papers/he-2020-deberta-decoding-enhanced-bert-disentangled/). In International Conference on Learning Representations. [↗](https://doi.org/10.48550/arxiv.2006.03654)
16. Michael A. Hedderich, Lukas Lange, Heike Adel, Jannik Strötgen, and Dietrich Klakow. 2021. [A survey on recent approaches for natural language processing in low-resource scenarios](https://md.research.elamur.ai/free/en/papers/hedderich-2021-survey-recent-approaches-natural-language/). In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 2545–2568, Online. Association for Computational Linguistics.
17. Janne Bondi Johannessen, Joel James Priestley, Kristin Hagen, Tor Anders Åfarli, and Øystein Alexander Vangsnes. 2009. The Nordic dialect corpus–an advanced research tool. In Proceedings of the 17th Nordic Conference of Computational Linguistics (NODALIDA 2009), pages 73–80, Odense, Denmark. Northern European Association for Language Technology (NEALT). [find](https://scholar.google.com/scholar?q=Janne+Bondi+Johannessen%2C+Joel+James+Priestley%2C+Kristin+Hagen%2C+Tor+Anders+%C3%85farli%2C+and+%C3%98ystein+Alexander+Vangsnes%2E+2009%2E+The+Nordic+dialect+corpus%E2%80%93an+advanced+research+tool%2E+In+Proceedings+of+the+17th+N)
18. Fredrik Jørgensen, Tobias Aasmoe, Anne-Stine Ruud Husevåg, Lilja Øvrelid, and Erik Velldal. 2020. NorNE: Annotating named entities for Norwegian. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 4547–4556, Marseille, France. European Language Resources Association. [↗](https://doi.org/10.48550/arxiv.1911.12146)
19. Xaver Maria Krückl, Verena Blaschke, and Barbara Plank. 2025. Improving dialectal slot and intent detection with auxiliary tasks: A multi-dialectal Bavarian case study. In Proceedings of the Twelfth Workshop on NLP for Similar Languages, Varieties, and Dialects (VarDial 2025), Abu Dhabi, UAE. International Committee on Computational Linguistics. [↗](https://doi.org/10.48550/arxiv.2501.03863)
20. Sang Yun Kwon, Gagan Bhatia, Elmoatez Billah Nagoudi, Alcides Alcoba Inciarte, and Muhammad Abdul-mageed. 2023. SIDLR: Slot and intent detection models for low-resource language varieties. In Tenth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial 2023), pages 241–250, Dubrovnik, Croatia. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Sang+Yun+Kwon%2C+Gagan+Bhatia%2C+Elmoatez+Billah+Nagoudi%2C+Alcides+Alcoba+Inciarte%2C+and+Muhammad+Abdul%2Dmageed%2E+2023%2E+SIDLR%3A+Slot+and+intent+detection+models+for+low%2Dresource+language+varieties%2E+In+Tenth+Wo)
21. John Lafferty, Andrew McCallum, Fernando Pereira, et al. 2001. Conditional random fields: Probabilistic models for segmenting and labeling sequence data. In Proceedings of the Eighteenth International Conference on Machine Learning, pages 282–289, San Francisco, CA, USA. Morgan Kaufmann Publishers Inc. [find](https://scholar.google.com/scholar?q=John+Lafferty%2C+Andrew+McCallum%2C+Fernando+Pereira%2C+et+al%2E+2001%2E+Conditional+random+fields%3A+Probabilistic+models+for+segmenting+and+labeling+sequence+data%2E+In+Proceedings+of+the+Eighteenth+International)
22. Haoran Li, Abhinav Arora, Shuohui Chen, Anchit Gupta, Sonal Gupta, and Yashar Mehdad. 2021. [MTOP: A comprehensive multilingual task-oriented semantic parsing benchmark](https://md.research.elamur.ai/free/en/papers/li-2021-mtop-comprehensive-multilingual-task-oriented/). In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 2950–2962, Online. Association for Computational Linguistics. [↗](https://doi.org/10.48550/arxiv.2008.09335)
23. Petter Mæhlum and Yves Scherrer. 2024. NoMusic - the Norwegian multi-dialectal slot and intent detection corpus. In Proceedings of the Eleventh Workshop on NLP for Similar Languages, Varieties, and Dialects (VarDial 2024), pages 107–116, Mexico City, Mexico. Association for Computational Linguistics. [↗](https://doi.org/10.48448/2cze-a959)
24. Sanad Malaysha, Mo El-Haj, Saad Ezzini, Mohammed Khalilia, Mustafa Jarrar, Sultan Almujaiwel, Ismail Berrada, and Houda Bouamor. 2024. [AraFinNLP 2024: The first Arabic financial NLP shared task](https://md.research.elamur.ai/free/en/papers/malaysha-2024-arafinnlp-2024-first-arabic-financial/). In Proceedings of The Second Arabic Natural Language Processing Conference, pages 393–402, Bangkok, Thailand. Association for Computational Linguistics. [↗](https://doi.org/10.48550/arxiv.2407.09818)
25. Syrielle Montariol, Arij Riabi, and Djamé Seddah. 2022. Multilingual auxiliary tasks training: Bridging the gap between languages for zero-shot transfer of hate speech detection models. In Findings of the Association for Computational Linguistics: AACL-IJCNLP 2022, pages 347–363, Online only. Association for Computational Linguistics. [↗](https://doi.org/10.48550/arxiv.2210.13029)
26. Alberto Muñoz-Ortiz, Verena Blaschke, and Barbara Plank. 2025. [Evaluating pixel language models on non-standardized languages](https://md.research.elamur.ai/free/en/papers/ortiz-2025-evaluating-pixel-language-models-non/). In Proceedings of the 31st International Conference on Computational Linguistics (COLING 2025), Abu Dhabi, UAE. International Committee on Computational Linguistics. [↗](https://doi.org/10.48550/arxiv.2412.09084)
27. Lilja Øvrelid, Andre Kåsen, Kristin Hagen, Anders Nøklestad, Per Erik Solberg, and Janne Bondi Johannessen. 2018. The LIA treebank of spoken Norwegian dialects. In Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018), Miyazaki, Japan. European Language Resources Association (ELRA). [↗](https://doi.org/10.63317/4jthgd5nvfw3)
28. Vishakh Padmakumar, Leonard Lausen, Miguel Ballesteros, Sheng Zha, He He, and George Karypis. 2022. Exploring the role of task transferability in large-scale multi-task learning. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 2542–2550, Seattle, United States. Association for Computational Linguistics. [↗](https://doi.org/10.48550/arxiv.2204.11117)
29. Clifton Poth, Jonas Pfeiffer, Andreas Rücklé, and Iryna Gurevych. 2021. [What to pre-train on? Efficient intermediate task selection](https://md.research.elamur.ai/free/en/papers/poth-2021-what-pre-train-efficient-intermediate/). In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 10585–10605, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
30. Yada Pruksachatkun, Jason Phang, Haokun Liu, Phu Mon Htut, Xiaoyi Zhang, Richard Yuanzhe Pang, Clara Vania, Katharina Kann, and Samuel R. Bowman. 2020. [Intermediate-task transfer learning with pretrained language models: When and why does it work?](https://md.research.elamur.ai/free/en/papers/pruksachatkun-2020-intermediate-task-transfer-learning-pretrained/) In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 5231–5247, Online. Association for Computational Linguistics.
31. Asmaa Ramadan, Manar Amr, Marwan Torki, and Nagwa El-Makky. 2024. [MA at AraFinNLP2024: BERT-based ensemble for cross-dialectal Arabic intent detection](https://md.research.elamur.ai/free/en/papers/ramadan-2024-ma-arafinnlp2024-bert-based-ensemble/). In Proceedings of The Second Arabic Natural Language Processing Conference, pages 441–445, Bangkok, Thailand. Association for Computational Linguistics.
32. Nils Reimers and Iryna Gurevych. 2019. [Sentence-BERT: Sentence embeddings using Siamese BERT-networks](https://md.research.elamur.ai/free/en/papers/reimers-2019-sentence-bert-sentence-embeddings-siamese/). 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 3982–3992, Hong Kong, China. Association for Computational Linguistics. [↗](https://doi.org/10.18653/v1/d19-1410)
33. Sebastian Ruder. 2017. [An overview of multi-task learning in deep neural networks](https://md.research.elamur.ai/free/en/papers/ruder-2017-overview-multi-task-learning-deep/). Preprint, arXiv:1706.05098. [↗](https://arxiv.org/abs/1706.05098)
34. David Samuel, Andrey Kutuzov, Samia Touileb, Erik Velldal, Lilja Øvrelid, Egil Rønningstad, Elina Sigdel, and Anna Palatkina. 2023. NorBench – a benchmark for Norwegian language models. In Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa), pages 618–633, Tórshavn, Faroe Islands. University of Tartu Library. [↗](https://doi.org/10.48550/arxiv.2305.03880)
35. Yves Scherrer, Rob van der Goot, and Petter Mæhlum. 2025. VarDial evaluation campaign 2025: Norwegian slot and intent detection and dialect identification (NorSID). In Proceedings of the Twelfth Workshop on NLP for Similar Languages, Varieties, and Dialects (VarDial 2025), Abu Dhabi, UAE. International Committee on Computational Linguistics. [find](https://scholar.google.com/scholar?q=Yves+Scherrer%2C+Rob+van+der+Goot%2C+and+Petter+M%C3%A6hlum%2E+2025%2E+VarDial+evaluation+campaign+2025%3A+Norwegian+slot+and+intent+detection+and+dialect+identification+%28NorSID%29%2E+In+Proceedings+of+the+Twelfth+Works)
36. Fynn Schröder and Chris Biemann. 2020. Estimating the influence of auxiliary tasks for multi-task learning of sequence tagging tasks. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 2971–2985, Online. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Fynn+Schr%C3%B6der+and+Chris+Biemann%2E+2020%2E+Estimating+the+influence+of+auxiliary+tasks+for+multi%2Dtask+learning+of+sequence+tagging+tasks%2E+In+Proceedings+of+the+58th+Annual+Meeting+of+the+Association+for+C)
37. Sebastian Schuster, Sonal Gupta, Rushin Shah, and Mike Lewis. 2019. [Cross-lingual transfer learning for multilingual task oriented dialog](https://md.research.elamur.ai/free/en/papers/schuster-2019-cross-lingual-transfer-learning-multilingual/). 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 3795–3805, Minneapolis, Minnesota. Association for Computational Linguistics. [↗](https://doi.org/10.48550/arxiv.1810.13327)
38. Vésteinn Snæbjarnarson, Annika Simonsen, Goran Glavaš, and Ivan Vulić. 2023. Transfer to a low-resource language via close relatives: The case study on Faroese. In Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa), pages 728–737, Tórshavn, Faroe Islands. University of Tartu Library. [↗](https://doi.org/10.48550/arxiv.2304.08823)
39. Per Erik Solberg, Arne Skjærholt, Lilja Øvrelid, Kristin Hagen, and Janne Bondi Johannessen. 2014. The Norwegian dependency treebank. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14), pages 789–795, Reykjavik, Iceland. European Language Resources Association (ELRA). [find](https://scholar.google.com/scholar?q=Per+Erik+Solberg%2C+Arne+Skj%C3%A6rholt%2C+Lilja+%C3%98vrelid%2C+Kristin+Hagen%2C+and+Janne+Bondi+Johannessen%2E+2014%2E+The+Norwegian+dependency+treebank%2E+In+Proceedings+of+the+Ninth+International+Conference+on+Language+R)
40. Aarohi Srivastava and David Chiang. 2023a. BERTwich: Extending BERT’s capabilities to model dialectal and noisy text. In Findings of the Association for Computational Linguistics: EMNLP • We replace ⟨L⟩ (/ó/, tjukk l ‘thick l’) with ⟨l⟩. While it can also correspond to ⟨rd⟩, we found that it much more often corresponds to ⟨l⟩ in the data. 2023, pages 15510–15521, Singapore. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Aarohi+Srivastava+and+David+Chiang%2E+2023a%2E+BERTwich%3A+Extending+BERT%E2%80%99s+capabilities+to+model+dialectal+and+noisy+text%2E+In+Findings+of+the+Association+for+Computational+Linguistics%3A+EMNLP+%E2%80%A2+We+replace+%E2%9F%A8)
41. Aarohi Srivastava and David Chiang. 2023b. Fine-tuning BERT with character-level noise for zero-shot transfer to dialects and closely-related languages. In Tenth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial 2023), pages 152–162, Dubrovnik, Croatia. Association for Computational Linguistics. • We remove apostrophes (originally used to mark syllabic consonants). [find](https://scholar.google.com/scholar?q=Aarohi+Srivastava+and+David+Chiang%2E+2023b%2E+Fine%2Dtuning+BERT+with+character%2Dlevel+noise+for+zero%2Dshot+transfer+to+dialects+and+closely%2Drelated+languages%2E+In+Tenth+Workshop+on+NLP+for+Similar+Languages%2C)

*Updated 1 November 2026*