---
title: "From Multiple-Choice to Extractive QA: A Case Study for English"
description: "Annotated data for task-specific NLP is scarce outside a few major languages. 71.0 F1. 31 references, cited by 1 paper here."
authors: ["Teresa Lynn", "Malik H. Altakrori", "Samar M. Magdy", "Rocktim Jyoti Das", "Chenyang Lyu", "Mohamed Nasr", "Younes Samih", "Kirill Chirkunov", "Alham Fikri Aji", "Preslav Nakov", "Shantanu Godbole", "Salim Roukos", "Radu Florian", "Nizar Habash"]
year: 2025
venue: "Proceedings of the 31st International Conference on Computational Linguistics"
source: "https://aclanthology.org/2025.coling-main.168/"
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/lynn-2025-multiple-choice-extractive-qa-case/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/lynn-2025-multiple-choice-extractive-qa-case/)

[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/14/) / From Multiple-Choice to Extractive QA: A Case Study for English and Arabic

# From Multiple-Choice to Extractive QA: A Case Study for English and Arabic

**Authors:** [Teresa Lynn](https://md.research.elamur.ai/free/en/authors/teresa-lynn/), [Malik H. Altakrori](https://md.research.elamur.ai/free/en/authors/malik-h-altakrori/), [Samar M. Magdy](https://md.research.elamur.ai/free/en/authors/samar-m-magdy/), [Rocktim Jyoti Das](https://md.research.elamur.ai/free/en/authors/rocktim-jyoti-das/), [Chenyang Lyu](https://md.research.elamur.ai/free/en/authors/chenyang-lyu/), Mohamed Nasr, [Younes Samih](https://md.research.elamur.ai/free/en/authors/younes-samih/), [Kirill Chirkunov](https://md.research.elamur.ai/free/en/authors/kirill-chirkunov/), [Alham Fikri Aji](https://md.research.elamur.ai/free/en/authors/alham-fikri-aji/), [Preslav Nakov](https://md.research.elamur.ai/free/en/authors/preslav-nakov/), Shantanu Godbole, [Salim Roukos](https://md.research.elamur.ai/free/en/authors/salim-roukos/), [Radu Florian](https://md.research.elamur.ai/free/en/authors/radu-florian/) and [Nizar Habash](https://md.research.elamur.ai/free/en/authors/nizar-habash/) · **Year:** 2025 · **Venue:** [Proceedings of the 31st International Conference on Computational Linguistics](https://md.research.elamur.ai/free/en/venues/coling/) ([COLING 2025](https://md.research.elamur.ai/free/en/venues/coling/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.coling-main.168/) · [PDF](https://aclanthology.org/2025.coling-main.168.pdf) · [OpenAlex](https://openalex.org/W4396243793)

**Citations:** 0 citations (OpenAlex, 2026-10-14) · 1 in our library, of the 149,439 papers whose bibliographies we read

## Summary
Annotated data for task-specific NLP is scarce outside a few major languages. The authors ask whether a dataset built for one QA format can be turned into another. They take part of BELEBELE, a multiple-choice reading-comprehension benchmark covering 122 language variants, and convert it into extractive QA (EQA), where the answer is a span marked in the passage. Working on English and Modern Standard Arabic (MSA), they classify how each original answer relates to the passage, filter out pairs that cannot be expressed as a span, and annotate spans following written guidelines. The result is a parallel EN–MSA EQA resource, released as BELEBELE-EQA. They benchmark it with PrimeQA in monolingual and cross-lingual settings, including questions in five Arabic dialects. Dialectal questions score clearly lower, and machine-translating them into EN or MSA first narrows much of the gap. Only directly matching answers convert cleanly, so conversion needs substantial manual effort. Still, the guidelines, the filtering approach and the option of projecting spans across languages make the method reusable for the other BELEBELE languages.

## Key points
- Source data: BELEBELE (Bandarkar et al., 2023), which pairs Flores-200 passages with four-option questions. Target: a parallel EQA set for EN and MSA, with guidelines meant to extend to the remaining 120 variants.
- Dialects tested: Egyptian (arz), Iraqi (acm), Moroccan (ary), Gulf/Najdi (ars) and North Levantine (apc). The model accepts dialectal questions but answers in MSA or EN.
- A taxonomy of answer–passage relations covers exact match, overlap, morphological variation, coreference, semantic similarity, paraphrase, entailment, context awareness, pragmatic knowledge, true/false and restricted answers. Only the Exact type resembles plain SQuAD-style QA. Filtering removed more than half of the pairs.
- Evaluation used PrimeQA (NQ+TyDi+SQuAD model).
  - EN passages: EN questions reach 71.0 F1. Raw dialect questions average 45.9 F1, rising to 63.9 when translated to EN first.
  - MSA passages: MSA questions reach 62.0 F1. Raw dialect questions average 52.1 F1, rising to 56.6 when translated to MSA via an EN pivot with Google Translate.
- Results are reported both raw and after text normalization (EM, F1, EM_n, F1_n). Moroccan is consistently the hardest dialect.

## Interesting ideas
- Each original answer is labelled by the kind of link that connects it to the passage, from exact match through coreference and paraphrase to pragmatic inference, which turns a format conversion into a diagnostic of required reasoning.
- Items that do not fit the target format are filtered out instead of being forced into it, and the rejected items are kept as a separate pool for later reformulation.
- Spans are annotated carefully in one language and then projected to parallel versions through translation, which bootstraps many languages from one verified set.
- Translating dialectal questions into the standard variety before answering recovers a large share of the lost accuracy, showing that normalizing input upstream pays off.
- Scores are reported both raw and after text normalization, which separates surface-format mismatches from genuine content errors.

## For Mova

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

- **I1** (answer): Tag school-test and fable QA items by the link type needed, so accuracy can be reported per category and failures traced to a specific missing capability.
- **I2** (learn): When converting multiple-choice tests into span-grounded training items, keep only those with a clean span and store the rest as a hard set for later study.
- **I3** (back): Answer spans could be carried through the meta-world graph, so a node grounded in the English text is located again in the generated or translated text.
- **I4** (tokens): A normalization pass that maps nonstandard or dialectal English spellings to standard forms before tagging could protect later stages from noisy input.
- **I5** (learn): Evaluation runs could always pair strict and normalized metrics, so a regression can be identified as either a formatting artefact or a real comprehension failure.

*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

- [Stanford University](https://md.research.elamur.ai/free/en/universities/stanford-university/) — University, Stanford, United States · 434 works · 314,419 citations
- [IBM](https://md.research.elamur.ai/free/en/companies/ibm/) — Company, Armonk, United States · 139 works · 70,691 citations
- [New York University Abu Dhabi](https://md.research.elamur.ai/free/en/universities/new-york-university-abu-dhabi/) — University, Abu Dhabi, United Arab Emirates · 122 works · 4,602 citations

📚 Shelves (5): [🖥️ 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 · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 2,869 works

🧭 Topics (3): [English](https://md.research.elamur.ai/free/en/topics/english/) · 2,263 works · [Semitic languages](https://md.research.elamur.ai/free/en/topics/semitic-languages/) · 2,908 works · [❓ Question answering](https://md.research.elamur.ai/free/en/topics/question-answering/) · 441 works

## Cite

Cite as: Teresa Lynn, Malik H. Altakrori, Samar M. Magdy, Rocktim Jyoti Das, Chenyang Lyu, Mohamed Nasr, Younes Samih, Kirill Chirkunov, Alham Fikri Aji, Preslav Nakov, Shantanu Godbole, Salim Roukos, Radu Florian and Nizar Habash. 2025. From Multiple-Choice to Extractive QA: A Case Study for English and Arabic. Proceedings of the 31st International Conference on Computational Linguistics.

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

```bibtex
@inproceedings{lynn2025multiple,
  title = {{From Multiple-Choice to Extractive QA: A Case Study for English and Arabic}},
  author = {Teresa Lynn, Malik H. Altakrori, Samar M. Magdy, Rocktim Jyoti Das, Chenyang Lyu, Mohamed Nasr, Younes Samih, Kirill Chirkunov, Alham Fikri Aji, Preslav Nakov, Shantanu Godbole, Salim Roukos, Radu Florian and Nizar Habash},
  booktitle = {Proceedings of the 31st International Conference on Computational Linguistics},
  year = {2025},
  url = {https://aclanthology.org/2025.coling-main.168/}
}
```

- [← previous From Form to Function: A Constructional NLI Benchmark](https://md.research.elamur.ai/free/en/papers/bonial-2025-form-function-constructional-nli-benchmark/)
- [next → From Test-taking to Cognitive Scaffolding: A Pedagogical Diagnostic Benchmark for LLMs on English Standardized Tests](https://md.research.elamur.ai/free/en/papers/tang-2025-test-taking-cognitive-scaffolding-pedagogical/)
- [↑ back to papers of 2025](https://md.research.elamur.ai/free/en/papers/2025/page/14/)

## References

31 references, 12 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Abdelrahman Abdallah, Mahmoud Kasem, Mahmoud Abdalla, Mohamed Mahmoud, Mohamed Elkasaby, Yasser Elbendary, and Adam Jatowt. 2024. [Arabicaqa: A comprehensive dataset for Arabic question answering](https://md.research.elamur.ai/free/en/papers/abdallah-2024-arabicaqa-comprehensive-dataset-arabic-question/). Preprint, arXiv:2403.17848. [↗](https://arxiv.org/abs/2403.17848)
2. Renlong Ai, Sebastian Krause, Walter Kasper, Feiyu Xu, and Hans Uszkoreit. 2015. Semi-automatic generation of multiple-choice tests from mentions of semantic relations. In Proceedings of the 2nd Workshop on Natural Language Processing Techniques for Educational Applications, pages 26–33, Beijing, China. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Renlong+Ai%2C+Sebastian+Krause%2C+Walter+Kasper%2C+Feiyu+Xu%2C+and+Hans+Uszkoreit%2E+2015%2E+Semi%2Dautomatic+generation+of+multiple%2Dchoice+tests+from+mentions+of+semantic+relations%2E+In+Proceedings+of+the+2nd+Works)
3. Tahani H Alwaneen, Aqil M Azmi, Hatim A Aboal-samh, Erik Cambria, and Amir Hussain. 2022. Arabic question answering system: a survey. Artificial Intelligence Review, 55(1):207–253. [↗](https://doi.org/10.1007/s10462-021-10031-1)
4. Mikel Artetxe, Sebastian Ruder, and Dani Yogatama. 2020. [On the cross-lingual transferability of monolingual representations](https://md.research.elamur.ai/free/en/papers/artetxe-2020-cross-lingual-transferability-monolingual-representations/). In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 4623–4637, Online. Association for Computational Linguistics.
5. Lucas Bandarkar, Davis Liang, Benjamin Muller, Mikel Artetxe, Satya Narayan Shukla, Donald Husa, Naman Goyal, Abhinandan Krishnan, Luke Zettlemoyer, and Madian Khabsa. 2023. [The Belebele benchmark: a parallel reading comprehension dataset in 122 language variants](https://md.research.elamur.ai/free/en/papers/bandarkar-2023-belebele-benchmark-parallel-reading-comprehension/). arXiv e-prints, pages arXiv–2308.
6. Mariam M Biltawi, Sara Tedmori, and Arafat Awajan. 2021. Arabic question answering systems: gap analysis. IEEE Access, 9:63876–63904. [↗](https://doi.org/10.1109/access.2021.3074950)
7. Steven Bird and Edward Loper. 2004. [NLTK: The natural language toolkit](https://md.research.elamur.ai/free/en/papers/bird-2006-nltk-natural-language-toolkit/). In Proceedings of the ACL Interactive Poster and Demonstration Sessions, pages 214–217, Barcelona, Spain. Association for Computational Linguistics.
8. Jonathan H. Clark, Eunsol Choi, Michael Collins, Dan Garrette, Tom Kwiatkowski, Vitaly Nikolaev, and Jennimaria Palomaki. 2020. [TyDi QA: A benchmark for information-seeking question answering in typologically diverse languages](https://md.research.elamur.ai/free/en/papers/clark-2020-tydi-qa-benchmark-information-seeking/). Transactions of the Association for Computational Linguistics, 8:454–470. [↗](https://doi.org/10.48550/arxiv.2003.05002)
9. 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. [↗](https://doi.org/10.18653/v1/2020.acl-main.747)
10. Dorottya Demszky, Kelvin Guu, and Percy Liang. 2018. Transforming question answering datasets into natural language inference datasets. arXiv preprint arXiv:1809.02922. [↗](https://arxiv.org/abs/1809.02922)
11. Fahim Faisal, Sharlina Keshava, Md Mahfuz Ibn Alam, and Antonios Anastasopoulos. 2021. Sd-qa: Spoken dialectal question answering for the real world. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 3296–3315. [find](https://scholar.google.com/scholar?q=Fahim+Faisal%2C+Sharlina+Keshava%2C+Md+Mahfuz+Ibn+Alam%2C+and+Antonios+Anastasopoulos%2E+2021%2E+Sd%2Dqa%3A+Spoken+dialectal+question+answering+for+the+real+world%2E+In+Findings+of+the+Association+for+Computational+L)
12. Charles A Ferguson. 1959. 15(2):325–340. Diglossia. [find](https://scholar.google.com/scholar?q=Charles+A+Ferguson%2E+1959%2E+15%282%29%3A325%E2%80%93340%2E+Diglossia%2E)
13. WORD, Amir Hadifar, Semere Kiros Bitew, Johannes Deleu, Chris Develder, and Thomas Demeester. 2023. Eduqg: A multi-format multiple-choice dataset for the educational domain. IEEE Access, 11:20885– 20896. [↗](https://doi.org/10.1109/access.2023.3248790)
14. Pratik Joshi, Sebastin Santy, Amar Budhiraja, Kalika Bali, and Monojit Choudhury. 2020. [The state and fate of linguistic diversity and inclusion in the NLP world](https://md.research.elamur.ai/free/en/papers/joshi-2020-state-fate-linguistic-diversity-inclusion/). In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 6282–6293, Online. Association for Computational Linguistics.
15. Nikiforos Karamanis, Le An Ha, and Ruslan Mitkov. 2006. Generating multiple-choice test items from medical text: A pilot study. In Proceedings of the Fourth International Natural Language Generation Conference, pages 111–113, Sydney, Australia. Association for Computational Linguistics. 1344, Santa Fe, New Mexico, USA. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Nikiforos+Karamanis%2C+Le+An+Ha%2C+and+Ruslan+Mitkov%2E+2006%2E+Generating+multiple%2Dchoice+test+items+from+medical+text%3A+A+pilot+study%2E+In+Proceedings+of+the+Fourth+International+Natural+Language+Generation+C)
16. Tushar Khot, Ashish Sabharwal, and Peter Clark. 2018. Scitail: A textual entailment dataset from science question answering. In Proceedings of the AAAI Conference on Artificial Intelligence, New Orleans, Louisiana. [find](https://scholar.google.com/scholar?q=Tushar+Khot%2C+Ashish+Sabharwal%2C+and+Peter+Clark%2E+2018%2E+Scitail%3A+A+textual+entailment+dataset+from+science+question+answering%2E+In+Proceedings+of+the+AAAI+Conference+on+Artificial+Intelligence%2C+New+Orlea)
17. Priyanka Sen, Alham Fikri Aji, and Amir Saffari. 2022. Mintaka: A complex, natural, and multilingual dataset for end-to-end question answering. In Proceedings of the 29th International Conference on Computational Linguistics, pages 1604–1619, Gyeongju, Republic of Korea. International Committee on Computational Linguistics. [↗](https://doi.org/10.48550/arxiv.2210.01613)
18. Ghader Kurdi, Jared Leo, Bijan Parsia, Uli Sattler, and Salam Al-Emari. 2020. A systematic review of automatic question generation for educational purposes. International Journal of Artificial Intelligence in Education, 30:121–204. [↗](https://doi.org/10.1007/s40593-019-00186-y)
19. Tom Kwiatkowski, Jennimaria Palomaki, Olivia Redfield, Michael Collins, Ankur Parikh, Chris Alberti, Danielle Epstein, Illia Polosukhin, Matthew Kelcey, Jacob Devlin, Kenton Lee, Kristina N. Toutanova, Llion Jones, Ming-Wei Chang, Andrew Dai, Jakob Uszkoreit, Quoc Le, and Slav Petrov. 2019. [Natural questions: a benchmark for question answering research](https://md.research.elamur.ai/free/en/papers/kwiatkowski-2019-natural-questions-benchmark-question-answering/). Transactions of the Association of Computational Linguistics. [↗](https://doi.org/10.1162/tacl_a_00276)
20. Patrick Lewis, Barlas Oguz, Ruty Rinott, Sebastian Riedel, and Holger Schwenk. 2020. [MLQA: Evaluating cross-lingual extractive question answering](https://md.research.elamur.ai/free/en/papers/lewis-2019-mlqa-evaluating-cross-lingual-extractive/). In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 7315– 7330, Online. Association for Computational Linguistics. [↗](https://doi.org/10.18653/v1/2020.acl-main.653)
21. Mohamed Shaheen and Ahmed Magdy Ezzeldin. 2014. Arabic question answering: systems, resources, tools, and future trends. Arabian Journal for Science and Engineering, 39:4541–4564. [↗](https://doi.org/10.1007/s13369-014-1062-2)
22. Avirup Sil, Jaydeep Sen, Bhavani Iyer, Martin Franz, Kshitij Fadnis, Mihaela Bornea, Sara Rosenthal, J Scott McCarley, Rong Zhang, Vishwajeet Kumar, et al. 2023. PrimeQA: The prime repository for state-of-the-art multilingual question answering research and development. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations), pages 51–62, Toronto, Canada. Association for Computational Linguistics. [↗](https://doi.org/10.48550/arxiv.2301.09715)
23. Ruslan Mitkov and Le An Ha. 2003. Computer-aided generation of multiple-choice tests. In Proceedings of the HLT-NAACL 03 Workshop on Building Educational Applications Using Natural Language Processing, pages 17–22. [find](https://scholar.google.com/scholar?q=Ruslan+Mitkov+and+Le+An+Ha%2E+2003%2E+Computer%2Daided+generation+of+multiple%2Dchoice+tests%2E+In+Proceedings+of+the+HLT%2DNAACL+03+Workshop+on+Building+Educational+Applications+Using+Natural+Language+Processing)
24. NLLB Team, Marta R. Costa-jussà, James Cross, Onur Çelebi, Maha Elbayad, Kenneth Heafield, Kevin Heffernan, Elahe Kalbassi, Janice Lam, Daniel Licht, Jean Maillard, Anna Sun, Skyler Wang, Guillaume Wenzek, Al Youngblood, Bapi Akula, Loic Barrault, Gabriel Mejia Gonzalez, Prangthip Hansanti, John Hoffman, Semarley Jarrett, Kaushik Ram Sadagopan, Dirk Rowe, Shannon Spruit, Chau Tran, Pierre Andrews, Necip Fazil Ayan, Shruti Bhosale, Sergey Edunov, Angela Fan, Cynthia Gao, Vedanuj Goswami, Francisco Guzmán, Philipp Koehn, Alexandre Mourachko, Christophe Ropers, Safiyyah Saleem, Holger Schwenk, and Jeff Wang. 2022. No language left behind: Scaling human-centered machine translation. Preprint, arXiv:2207.04672. [↗](https://arxiv.org/abs/2207.04672)
25. Hussein Mozannar, Elie Maamary, Karl El Hajal, and Hazem Hajj. 2019. [Neural Arabic question answering](https://md.research.elamur.ai/free/en/papers/mozannar-2019-neural-arabic-question-answering/). In Proceedings of the Fourth Arabic Natural Language Processing Workshop, pages 108–118, Florence, Italy. Association for Computational Linguistics.
26. Jörg Tiedemann and Santhosh Thottingal. 2020. OPUS-MT – building open translation services for the world. In Proceedings of the 22nd Annual Conference of the European Association for Machine Translation, pages 479–480, Lisboa, Portugal. European Association for Machine Translation. [find](https://scholar.google.com/scholar?q=J%C3%B6rg+Tiedemann+and+Santhosh+Thottingal%2E+2020%2E+OPUS%2DMT+%E2%80%93+building+open+translation+services+for+the+world%2E+In+Proceedings+of+the+22nd+Annual+Conference+of+the+European+Association+for+Machine+Translati)
27. Yann Mathet, Antoine Widlöcher, and Jean-Philippe Métivier. 2015. The unified and holistic method gamma (γ) for inter-annotator agreement measure and alignment. Computational Linguistics, 41(3):437–479. [↗](https://doi.org/10.1162/coli_a_00227)
28. Pranav Rajpurkar, Jian Zhang, Konstantin Lopyrev, and Percy Liang. 2016. [SQuAD: 100,000+ questions for machine comprehension of text](https://md.research.elamur.ai/free/en/papers/rajpurkar-2016-squad-100-000-questions-machine/). In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 2383–2392, Austin, Texas. Association for Computational Linguistics. [↗](https://doi.org/10.18653/v1/d16-1264)
29. Georg Rehm and Andy Way. 2023. European Language Equality: Introduction, pages 1–10. Springer International Publishing, Cham. [find](https://scholar.google.com/scholar?q=Georg+Rehm+and+Andy+Way%2E+2023%2E+European+Language+Equality%3A+Introduction%2C+pages+1%E2%80%9310%2E+Springer+International+Publishing%2C+Cham%2E)
30. Mohammad Salameh, Houda Bouamor, and Nizar Habash. 2018. [Fine-grained Arabic dialect identification](https://md.research.elamur.ai/free/en/papers/salameh-2018-fine-grained-arabic-dialect-identification/). In Proceedings of the 27th International Conference on Computational Linguistics, pages 1332– Zhen Wang. 2022. Modern question answering datasets and benchmarks: A survey. arXiv e-prints.
31. Thomas Wolf, Lysandre Debut, Victor Sanh, Julien Chaumond, Clement Delangue, Anthony Moi, Pier-ric Cistac, Tim Rault, Remi Louf, Morgan Funtowicz, Joe Davison, Sam Shleifer, Patrick von Platen, Clara Ma, Yacine Jernite, Julien Plu, Canwen Xu, Teven Le Scao, Sylvain Gugger, Mariama Drame, Quentin Lhoest, and Alexander Rush. 2020. [Transformers: State-of-the-art natural language processing](https://md.research.elamur.ai/free/en/papers/wolf-2020-transformers-state-art-natural-language/). In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 38–45, Online. Association for Computational Linguistics. [↗](https://doi.org/10.18653/v1/2020.emnlp-demos.6)

*Updated 1 November 2026*