Elamur Research⌕
☰
home / papers / 2023 / MasakhaNEWS: News Topic Classification for African languages

MasakhaNEWS: News Topic Classification for African languages

Paper · 2023 · David Ifeoluwa Adelani, Marek Masiak, Israel Abebe Azime et al.

Summary

African languages are spoken by about a fifth of humanity, yet they have few evaluation datasets. Most existing news topic resources cover single languages, use inconsistent label sets, or were labelled with little human oversight. MasakhaNEWS addresses this gap. It is a news topic classification benchmark for 16 languages widely used in Africa, including English and French, and every language uses the same label scheme. Articles were crawled from BBC and VOA sites and labelled by native-speaking volunteers from the Masakhane community.

The authors set baselines with classical machine-learning classifiers and fine-tuned language models. They then tested methods meant for settings with little or no labelled data:

  • MAD-X cross-lingual adapters
  • PET
  • SetFit
  • the co:here embedding API
  • zero-shot prompting of GPT-3.5-Turbo and GPT-4

Full supervision reaches 92.6 F1 on average. PET with only 10 labelled examples per class reaches 86.0 F1, which is more than 90% of that score. The work shows that standard NLP techniques transfer well to African languages and that a handful of annotations can go a long way.

Key points

  • Coverage: 16 languages from four families (Niger-Congo, Afro-Asiatic, Indo-European, English Creole/Naija). They span West, East, Central and Southern Africa, and each language has at least 10 million speakers.
  • Data collection:
    • Between 2k and 12k articles were crawled per language from BBC and VOA.
    • The target was about 3,000 annotated articles per language. Lingala, Rundi and Somali fell short of this.
  • Label set: eight categories. Six come from BBC English (business, entertainment, health, politics, sports, technology). The authors added "religion" and "uncategorized".
  • Few-shot results:
    • PET averages 81.9 F1 at 5 shots, 86.0 at 10, 87.9 at 20 and 89.9 at 50, against 92.6 for full supervision.
    • With only 5 shots, PET is roughly as good as SetFit or co:here with 50 shots.
    • PET does use extra unlabelled text, which SetFit and co:here do not.
  • Zero-shot prompting:
    • GPT-3.5-Turbo does well on Latin-script languages but poorly on Amharic and Tigrinya.
    • GPT-4 closes most of that gap, roughly matching cross-lingual transfer from a related African language.
  • Release: data and code are on GitHub under an academic license or CC BY-NC 4.0.

Interesting ideas

  • I1. Shared label set built from a reference outlet: The authors adopted BBC English's categories and added only the classes that local news needed (religion, uncategorized). This keeps results comparable across languages while still fitting each language's news, a useful pattern for any multilingual benchmark, including Ukrainian-centric ones.
  • I2. Reusing site metadata for pre-filtering: Where a news site already tagged its articles, those tags were used to drop off-topic material before human labelling. This is a cheap way to cut annotation effort when building a corpus from crawled web text.
  • I3. Comparing results by script: Separating LLM results by writing system revealed that GPT-3.5-Turbo's weakness was tied to non-Latin scripts. Similar breakdowns by script or tokenization could expose hidden weaknesses for Cyrillic or other scripts.
  • I4. Learning curve across shot counts: Evaluating each method at 5, 10, 20 and 50 shots, against a fully supervised ceiling, shows how many labels a new language actually needs. Here about 10 per class already gave most of the benefit, which helps plan annotation budgets.
  • I5. Noting reproducibility risks of commercial APIs: The authors state openly that results from ChatGPT and co:here may drift as the providers update their models. Any evaluation that relies on such APIs should record the model version and the query date.

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

🎓University of AmsterdamAmsterdam · Netherlands89 works · 81,337 citations🎓Fudan UniversityShanghai · China65 works · 19,402 citations🎓Saarland UniversitySaarbrücken · Germany102 works · 17,447 citations🎓University College LondonLondon · United Kingdom59 works · 16,463 citations🎓University of WaterlooWaterloo · Canada44 works · 12,783 citations🎓McGill UniversityMontreal · Canada51 works · 10,476 citations🔬Mila - Quebec Artificial Intelligence InstituteMontreal · Canada31 works · 13,061 citations🎓Technical University of MunichMunich · Germany18 works · 48,618 citations🎓University of California, DavisDavis · United States13 works · 41,713 citations🎓Paderborn UniversityPaderborn · Germany9 works · 3,554 citations🎓Instituto Politécnico NacionalMexico City · Mexico9 works · 4,150 citations🎓Lancaster UniversityLancaster · United Kingdom16 works · 1,153 citations🎓Universidade do PortoPorto · Portugal11 works · 1,963 citations🎓Iowa State UniversityAmes · United States4 works · 359 citations🔬Insight SFI Research Centre for Data AnalyticsDublin · Ireland5 works · 531 citations🎓Aston UniversityBirmingham · United Kingdom3 works · 201 citations🎓Makerere UniversityKampala · Uganda6 works · 885 citations🤝African Institute for Mathematical Sciences SenegalMbour · Senegal3 works · 531 citations🎓Ahmadu Bello UniversityZaria · Nigeria3 works · 358 citations🎓Montclair State UniversityMontclair · United States2 works · 84 citations🎓Luleå University of TechnologyLuleå · Sweden3 works · 660 citations🎓Haramaya UniversityDire Dawa · Ethiopia2 works · 150 citations🎓Wuhan University of TechnologyWuhan · China2 works · 84 citations

Also on the byline: National Open University of Nigeria · College of Saint Rose · Nnamdi Azikiwe University · Université du Burundi · Botswana International University of Science and Technology · Kaduna State University · Somali National University · Dire Dawa University · University of Rwanda · African Institute for Mathematical Sciences · Jamhuriya University of Science and Technology · Pan African University Institute for Basic Sciences, Technology and Innovation.

📚 Shelves 4 Computer Science · 9,086 works Artificial Intelligence · 8,889 works Arts and Humanities · 9,296 works Language and Linguistics · 9,206 works

Cite

Cite as David Ifeoluwa Adelani, Marek Masiak, Israel Abebe Azime, Jesujoba Alabi, Atnafu Lambebo Tonja, Christine Mwase, Odunayo Ogundepo, Bonaventure F. P. Dossou, Akintunde Oladipo, Doreen Nixdorf, Chris Chinenye Emezue, Sana Al-azzawi, Blessing Sibanda, Davis David, Lolwethu Ndolela, Jonathan Mukiibi, Tunde Ajayi, Tatiana Moteu, Brian Odhiambo, Abraham Owodunni, Nnaemeka Obiefuna, Muhidin Mohamed, Shamsuddeen Hassan Muhammad, Teshome Mulugeta Ababu, Saheed Abdullahi Salahudeen, Mesay Gemeda Yigezu, Tajuddeen Gwadabe, Idris Abdulmumin, Mahlet Taye, Oluwabusayo Awoyomi, Iyanuoluwa Shode, Tolulope Adelani, Habiba Abdulganiyu, Abdul-Hakeem Omotayo, Adetola Adeeko, Abeeb Afolabi, Anuoluwapo Aremu, Olanrewaju Samuel, Clemencia Siro, Wangari Kimotho, Onyekachi Ogbu, Chinedu Mbonu, Chiamaka Chukwuneke, Samuel Fanijo, Jessica Ojo, Oyinkansola Awosan, Tadesse Kebede, Toadoum Sari Sakayo, Pamela Nyatsine, Freedmore Sidume, Oreen Yousuf, Mardiyyah Oduwole, Kanda Tshinu, Ussen Kimanuka, Thina Diko, Siyanda Nxakama, Sinodos Nigusse, Abdulmejid Johar, Shafie Mohamed, Fuad Mire Hassan, Moges Ahmed Mehamed, Evrard Ngabire, Jules Jules, Ivan Ssenkungu and Pontus Stenetorp. 2023. MasakhaNEWS: News Topic Classification for African languages. 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).

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2023.ijcnlp-main.10

@inproceedings{adelani2023masakhanews,
  title = {{MasakhaNEWS: News Topic Classification for African languages}},
  author = {David Ifeoluwa Adelani, Marek Masiak, Israel Abebe Azime, Jesujoba Alabi, Atnafu Lambebo Tonja, Christine Mwase, Odunayo Ogundepo, Bonaventure F. P. Dossou, Akintunde Oladipo, Doreen Nixdorf, Chris Chinenye Emezue, Sana Al-azzawi, Blessing Sibanda, Davis David, Lolwethu Ndolela, Jonathan Mukiibi, Tunde Ajayi, Tatiana Moteu, Brian Odhiambo, Abraham Owodunni, Nnaemeka Obiefuna, Muhidin Mohamed, Shamsuddeen Hassan Muhammad, Teshome Mulugeta Ababu, Saheed Abdullahi Salahudeen, Mesay Gemeda Yigezu, Tajuddeen Gwadabe, Idris Abdulmumin, Mahlet Taye, Oluwabusayo Awoyomi, Iyanuoluwa Shode, Tolulope Adelani, Habiba Abdulganiyu, Abdul-Hakeem Omotayo, Adetola Adeeko, Abeeb Afolabi, Anuoluwapo Aremu, Olanrewaju Samuel, Clemencia Siro, Wangari Kimotho, Onyekachi Ogbu, Chinedu Mbonu, Chiamaka Chukwuneke, Samuel Fanijo, Jessica Ojo, Oyinkansola Awosan, Tadesse Kebede, Toadoum Sari Sakayo, Pamela Nyatsine, Freedmore Sidume, Oreen Yousuf, Mardiyyah Oduwole, Kanda Tshinu, Ussen Kimanuka, Thina Diko, Siyanda Nxakama, Sinodos Nigusse, Abdulmejid Johar, Shafie Mohamed, Fuad Mire Hassan, Moges Ahmed Mehamed, Evrard Ngabire, Jules Jules, Ivan Ssenkungu and Pontus Stenetorp},
  booktitle = {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)},
  year = {2023},
  doi = {10.18653/v1/2023.ijcnlp-main.10},
  url = {https://doi.org/10.18653/v1/2023.ijcnlp-main.10}
}

References

50 references, 30 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. David Adelani, Jesujoba Alabi, Angela Fan, Julia Kreutzer, Xiaoyu Shen, Machel Reid, Dana Ruiter, Dietrich Klakow, Peter Nabende, Ernie Chang, Tajuddeen Gwadabe, Freshia Sackey, Bonaventure F. P. Dossou, Chris Emezue, Colin Leong, Michael Beukman, Shamsuddeen Muhammad, Guyo Jarso, Oreen Yousuf, Andr…
  2. David Ifeoluwa Adelani, Jade Abbott, Graham Neubig, Daniel D’souza, Julia Kreutzer, Constantine Lignos, Chester Palen-Michel, Happy Buzaaba, Shruti Rijhwani, Sebastian Ruder, Stephen Mayhew, Israel Abebe Azime, Shamsuddeen H. Muhammad, Chris Chinenye Emezue, Joyce Nakatumba-Nabende, Perez Ogayo, Are…
  3. David Ifeoluwa Adelani, Graham Neubig, Sebastian Ruder, Shruti Rijhwani, Michael Beukman, Chester Palen-Michel, Constantine Lignos, Jesujoba O. Alabi, Shamsuddeen H. Muhammad, Peter Nabende, Cheikh M. Bamba Dione, Andiswa Bukula, Rooweither Mabuya, Bonaventure F. P. Dossou, Blessing Sibanda, Happy B…
  4. Jesujoba O. Alabi, David Ifeoluwa Adelani, Marius Mosbach, and Dietrich Klakow. 2022. Adapting pre-trained language models to African languages via multilingual adaptive fine-tuning. In Proceedings of the 29th International Conference on Computational Linguistics, pages 4336–4349, Gyeongju, Republic…
  5. Rahul Aralikatte, Ziling Cheng, Sumanth Doddapaneni, and Jackie Chi Kit Cheung. 2023. Vārta: A large-scale headline-generation dataset for indic languages. ArXiv, abs/2305.05858. find
  6. Israel Abebe Azime and Nebil Mohammed. 2021. An amharic news text classification dataset. CoRR, abs/2103.05639.
  7. David Blei, Andrew Ng, and Michael Jordan. 2001. Latent dirichlet allocation. In Advances in Neural Information Processing Systems, volume 14. MIT Press.
  8. Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel Ziegler, Jeffrey Wu, Clemens Winter, Chri…
  9. Hyung Won Chung, Thibault Fevry, Henry Tsai, Melvin Johnson, and Sebastian Ruder. 2021. Rethinking embedding coupling in pre-trained language models. In International Conference on Learning Representations.
  10. Hyung Won Chung, Le Hou, Shayne Longpre, Barret Zoph, Yi Tay, William Fedus, Eric Li, Xuezhi Wang, Mostafa Dehghani, Siddhartha Brahma, Albert Webson, Shixiang Shane Gu, Zhuyun Dai, Mirac Suzgun, Xinyun Chen, Aakanksha Chowdhery, Sharan Narang, Gaurav Mishra, Adams Yu, Vincent Zhao, Yanping Huang, A…
  11. Kevin Clark, Minh-Thang Luong, Quoc V. Le, and Christopher D. Manning. 2020. ELECTRA: Pre-training text encoders as discriminators rather than generators. In ICLR. find
  12. 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 fo… find
  13. Adji B. Dieng, Francisco J. R. Ruiz, and David M. Blei. 2020. Topic modeling in embedding spaces. Transactions of the Association for Computational Linguistics, 8:439–453.
  14. Bonaventure FP Dossou, Atnafu Lambebo Tonja, Oreen Yousuf, Salomey Osei, Abigail Oppong, Iyanuoluwa Shode, Oluwabusayo Olufunke Awoyomi, and Chris Chinenye Emezue. 2022. Afrolm: A self-active learning-based multilingual pretrained language model for 23 african languages. arXiv preprint arXiv:2211.03… find
  15. David M. Eberhard, Gary F. Simons, and Charles D. Fennig. 2021. Ethnologue: Languages of the world. twenty-third edition. find
  16. Fangxiaoyu Feng, Yinfei Yang, Daniel Cer, Naveen Arivazhagan, and Wei Wang. 2022. Language-agnostic BERT sentence embedding. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 878–891, Dublin, Ireland. Association for Computation…
  17. Awet Fesseha, Shengwu Xiong, Eshete Derb Emiru, Moussa Diallo, and Abdelghani Dahou. 2021. Text classification based on convolutional neural networks and word embedding for low-resource languages: Tigrinya. Information, 12(2). find
  18. J.L. Fleiss et al. 1971. Measuring nominal scale agreement among many raters. Psychological Bulletin, 76(5):378–382. find
  19. Tianyu Gao, Adam Fisch, and Danqi Chen. 2021. Making pre-trained language models better few-shot learners. 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), pa…
  20. Derek Greene and Pádraig Cunningham. 2006. Practical solutions to the problem of diagonal dominance in kernel document clustering. In Proceedings of the 23rd International Conference on Machine Learning, ICML ’06, page 377–384, New York, NY, USA. Association for Computing Machinery. find
  21. Pengcheng He, Jianfeng Gao, and Weizhu Chen. 2021a. Debertav3: Improving deberta using electra-style pre-training with gradient-disentangled embedding sharing. ArXiv, abs/2111.09543. in Natural Language Processing, pages 9019–9052, Abu Dhabi, United Arab Emirates. Association for Computational Lingu…
  22. Pengfei Liu, Weizhe Yuan, Jinlan Fu, Zhengbao Jiang, Hiroaki Hayashi, and Graham Neubig. 2023. Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing. ACM Comput. Surv., 55(9).
  23. Pengcheng He, Xiaodong Liu, Jianfeng Gao, and Weizhu Chen. 2021b. Deberta: Decoding-enhanced bert with disentangled attention. In International Conference on Learning Representations.
  24. Michael A. Hedderich, David Adelani, Dawei Zhu, Jesujoba Alabi, Udia Markus, and Dietrich Klakow. 2020. Transfer learning and distant supervision for multilingual transformer models: A study on African languages. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processi… find
  25. Neil Houlsby, Andrei Giurgiu, Stanislaw Jastrzebski, Bruna Morrone, Quentin de Laroussilhe, Andrea Gesmundo, Mona Attariyan, and Sylvain Gelly. 2019. Parameter-efficient transfer learning for nlp. In International Conference on Machine Learning. find
  26. Armand Joulin, Edouard Grave, Piotr Bojanowski, and Tomas Mikolov. 2017. Bag of tricks for efficient text classification. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers, pages 427–431, Valencia, Spain. Associatio… find
  27. Odunayo Jude Ogundepo, Akintunde Oladipo, Mofetoluwa Adeyemi, Kelechi Ogueji, and Jimmy Lin. 2022. AfriTeVA: Extending ?small data? pretraining approaches to sequence-to-sequence models. In Proceedings of the Third Workshop on Deep Learning for Low-Resource Natural Language Processing, pages 126–135… find
  28. Anoop Kunchukuttan, Divyanshu Kakwani, Satish Golla, Gokul N.C., Avik Bhattacharyya, Mitesh M. Khapra, and Pratyush Kumar. 2020. Ai4bharat-indicnlp corpus: Monolingual corpora and word embeddings for indic languages. arXiv preprint arXiv:2005.00085. — [arXiv:2005.00085](https://arxiv.org/abs/2005.00085) find
  29. Anne Lauscher, Vinit Ravishankar, Ivan Vulić, and Goran Glavaš. 2020. From zero to hero: On the limitations of zero-shot language transfer with multilingual Transformers. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 4483–4499, Online. Asso…
  30. Xi Victoria Lin, Todor Mihaylov, Mikel Artetxe, Tianlu Wang, Shuohui Chen, Daniel Simig, Myle Ott, Naman Goyal, Shruti Bhosale, Jingfei Du, Ramakanth Pasunuru, Sam Shleifer, Punit Singh Koura, Vishrav Chaudhary, Brian O’Horo, Jeff Wang, Luke Zettlemoyer, Zornitsa Kozareva, Mona Diab, Veselin Stoyano…
  31. Niklas Muennighoff, Thomas Wang, Lintang Sutawika, Adam Roberts, Stella Biderman, Teven Le Scao, M Saiful Bari, Sheng Shen, Zheng-Xin Yong, Hailey Schoelkopf, Xiangru Tang, Dragomir Radev, Alham Fikri Aji, Khalid Almubarak, Samuel Albanie, Zaid Alyafeai, Albert Webson, Edward Raff, and Colin Raffel.…
  32. Shamsuddeen Hassan Muhammad, Idris Abdulmumin, Abinew Ali Ayele, Nedjma Ousidhoum, David Ifeoluwa Adelani, Seid Muhie Yimam, Ibrahim Sa’id Ahmad, Meriem Beloucif, Saif Mohammad, Sebastian Ruder, Oumaima Hourrane, Pavel Brazdil, Felermino Dário Mário António Ali, Davis Davis, Salomey Osei, Bello Sheh…
  33. Rubungo Andre Niyongabo, Qu Hong, Julia Kreutzer, and Li Huang. 2020. KINNEWS and KIRNEWS: Benchmarking cross-lingual text classification for Kinyarwanda and Kirundi. In Proceedings of the 28th International Conference on Computational Linguistics, pages 5507–5521, Barcelona, Spain (Online). Interna… find
  34. NLLB-Team, Marta Ruiz Costa-jussà, James Cross, Onur cCelebi, Maha Elbayad, Kenneth Heafield, Kevin Heffernan, Elahe Kalbassi, Janice Lam, Daniel Licht, Jean Maillard, Anna Sun, Skyler Wang, Guillaume Wenzek, Alison Youngblood, Bapi Akula, Loïc Barrault, Gabriel Mejia Gonzalez, Prangthip Hansanti, J… find
  35. M Saiful Bari, Canwen Xu, Urmish Thakker, Shanya Sharma Sharma, Eliza Szczechla, Taewoon Kim, Gunjan Chhablani, Nihal Nayak, Debajyoti Datta, Jonathan Chang, Mike Tian-Jian Jiang, Han Wang, Matteo Manica, Sheng Shen, Zheng Xin Yong, Harshit Pandey, Rachel Bawden, Thomas Wang, Trishala Neeraj, Jos Ro…
  36. Kelechi Ogueji, Yuxin Zhu, and Jimmy Lin. 2021. Small data? no problem! exploring the viability of pretrained multilingual language models for low-resourced languages. In Proceedings of the 1st Workshop on Multilingual Representation Learning, pages 116–126, Punta Cana, Dominican Republic. Associati…
  37. Long Ouyang, Jeff Wu, Xu Jiang, Diogo Almeida, Carroll L. Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, John Schulman, Jacob Hilton, Fraser Kelton, Luke E. Miller, Maddie Simens, Amanda Askell, Peter Welinder, Paul Francis Christiano, Jan Leike, and Ryan J. Low…
  38. F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, M. Brucher, M. Perrot, and E. Duchesnay. 2011. Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12:282… find
  39. Jonas Pfeiffer, Ivan Vulić, Iryna Gurevych, and Sebastian Ruder. 2020. MAD-X: An Adapter-Based Framework for Multi-Task Cross-Lingual Transfer. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 7654–7673, Online. Association for Computational L…
  40. Jonas Pfeiffer, Ivan Vulić, Iryna Gurevych, and Sebastian Ruder. 2021. UNKs everywhere: Adapting multilingual language models to new scripts. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 10186–10203, Online and Punta Cana, Dominican Republic. Asso…
  41. Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J. Liu. 2020. Exploring the limits of transfer learning with a unified text-to-text transformer. Journal of Machine Learning Research, 21(140):1–67.
  42. Teven Le Scao, Angela Fan, Christopher Akiki, Elizabeth-Jane Pavlick, Suzana Ili’c, Daniel Hesslow, Roman Castagn’e, Alexandra Sasha Luccioni, Franccois Yvon, Matthias Gallé, Jonathan Tow, Alexander M. Rush, Stella Rose Biderman, Albert Webson, Pawan Sasanka Ammanamanchi, Thomas Wang, Benoît Sagot,… find
  43. Timo Schick and Hinrich Schütze. 2021a. Exploiting cloze-questions for few-shot text classification and natural language inference. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 255–269, Online. Association for Comp…
  44. Timo Schick and Hinrich Schütze. 2021b. It’s not just size that matters: Small language models are also few-shot learners. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 2339–2352, Online. Assoc…
  45. Nils Reimers and Iryna Gurevych. 2019. Sentence-bert: Sentence embeddings using siamese bert-networks. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics.
  46. Taylor Shin, Yasaman Razeghi, Robert L. Logan IV, Eric Wallace, and Sameer Singh. 2020. AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 4222–4235, Onlin…
  47. Victor Sanh, Albert Webson, Colin Raffel, Stephen Bach, Lintang Sutawika, Zaid Alyafeai, Antoine Chaffin, Arnaud Stiegler, Arun Raja, Manan Dey, Iyanuoluwa Shode, David Ifeoluwa Adelani, and Anna Feldman. 2022. yosm: A new yoruba sentiment corpus for movie reviews. find
  48. Iyanuoluwa Shode, David Ifeoluwa Adelani, JIng Peng, and Anna Feldman. 2023. NollySenti: Leveraging transfer learning and machine translation for Nigerian movie sentiment classification. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Paper… find
  49. Chi Sun, Xipeng Qiu, Yige Xu, and Xuanjing Huang. 2019. How to fine-tune bert for text classification? In China National Conference on Chinese Computational Linguistics.
  50. Lewis Tunstall, Nils Reimers, Unso Eun Seo Jo, Luke Bates, Daniel Korat, Moshe Wasserblat, and Oren Pereg. 2022a. Efficient few-shot learning without prompts. ArXiv, abs/2209.11055. — [arXiv:2209.11055](https://arxiv.org/abs/2209.11055) find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/adelani-2023-masakhanews-news-topic-classification-african/