---
title: "Translation-Augmented Multilingual Summarization for"
description: "The paper creates data by machine-translating an XSum sample (2,000/400/500 train/validation/test pairs) into Swahili, Hausa… 18 references."
authors: ["Prasanth Yadla"]
year: 2026
venue: "Proceedings of the Sixth Workshop on Language Technology for Equality, Diversity, Inclusion"
source: "https://aclanthology.org/2026.ltedi-1.10/"
doi: "10.18653/v1/2026.ltedi-1.10"
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/yadla-2026-translation-augmented-multilingual-summarization-low/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/yadla-2026-translation-augmented-multilingual-summarization-low/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/54/) / Translation-Augmented Multilingual Summarization for Low-Resource Languages

# Translation-Augmented Multilingual Summarization for Low-Resource Languages

**Authors:** [Prasanth Yadla](https://md.research.elamur.ai/free/en/authors/prasanth-yadla/) · **Year:** 2026 · **Venue:** [Proceedings of the Sixth Workshop on Language Technology for Equality, Diversity, Inclusion](https://md.research.elamur.ai/free/en/venues/ltedi/) ([Workshop on Language Technology for Equality, Diversity, Inclusion 2026](https://md.research.elamur.ai/free/en/venues/ltedi/2026/)) · **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/2026.ltedi-1.10/) · [PDF](https://aclanthology.org/2026.ltedi-1.10.pdf) · [DOI 10.18653/v1/2026.ltedi-1.10](https://doi.org/10.18653/v1/2026.ltedi-1.10) · [OpenAlex](https://openalex.org/W7166802896)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
Summarization tools are mature for English but scarce for low-resource languages, largely because labeled data is lacking. The paper creates data by machine-translating an XSum sample (2,000/400/500 train/validation/test pairs) into Swahili, Hausa and Afrikaans with NLLB-200-distilled-600M, translating both articles and reference summaries. Using mBART-large-50, the author compares three fine-tuning regimes against Zero-shot and Lead-3 baselines, all scored with ROUGE:

- **MONO:** a separate model trained for each language.
- **XLT:** English-only training applied directly to the target languages.
- **TAMT:** joint training on English plus all translations.

MONO performs best for Swahili and Afrikaans and beats Lead-3 there. For Hausa, English-only transfer stays ahead. The author attributes this split to whether mBART-50 has a dedicated language token: Hausa lacks one and must borrow en_XX. TAMT never wins, so the anticipated TAMT > MONO > XLT ranking does not hold. For anyone building MT-derived datasets for under-served languages, the study identifies model vocabulary coverage as a decisive factor. Data, code and checkpoints are openly released.

## Key points
- ROUGE-L with MONO: Swahili 13.9 vs. Lead-3 13.3, and Afrikaans 15.7 vs. Lead-3 14.7. For Hausa, XLT is the best neural method at 14.5, but Lead-3 still ranks first overall.
- Observed rankings:
  - Swahili: MONO > Lead-3 > Zero-shot > TAMT > XLT
  - Hausa: Lead-3 > XLT > Zero-shot > TAMT > MONO
  - Afrikaans: MONO > Lead-3 > Zero-shot > XLT > TAMT
- Setup: mBART-large-50 (~610M parameters), AdamW with learning rate 3 × 10⁻⁵, 2 epochs. Native tokens sw_KE and af_ZA are used; Hausa falls back to en_XX.
- Cost trade-off: MONO needs one checkpoint per language (3× XLT compute here). TAMT uses the same data volume in a single shared model, which the author argues scales better to many languages.
- Limitations:
  - Both training data and evaluation references are machine translations, so they carry English-centric framing and translation errors (e.g., a literal Swahili rendering of "hen party").
  - Training scale is small.
  - Human evaluation is only proposed, not carried out.

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

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works

🧭 Topics (3): [🌍 Multilingual & cross-lingual NLP](https://md.research.elamur.ai/free/en/topics/multilingual-nlp/) · 882 works · [📝 Summarization](https://md.research.elamur.ai/free/en/topics/summarization/) · 243 works · [🌱 Low-resource languages](https://md.research.elamur.ai/free/en/topics/low-resource-languages/) · 287 works

## Cite

Cite as: Prasanth Yadla. 2026. Translation-Augmented Multilingual Summarization for Low-Resource Languages. Proceedings of the Sixth Workshop on Language Technology for Equality, Diversity, Inclusion.

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

```bibtex
@inproceedings{yadla2026translation,
  title = {{Translation-Augmented Multilingual Summarization for Low-Resource Languages}},
  author = {Prasanth Yadla},
  booktitle = {Proceedings of the Sixth Workshop on Language Technology for Equality, Diversity, Inclusion},
  year = {2026},
  doi = {10.18653/v1/2026.ltedi-1.10},
  url = {https://doi.org/10.18653/v1/2026.ltedi-1.10}
}
```

- [← previous Translation with Thought: Difficulty-Adaptive Reasoning via Reinforcement Learning for Multi-Domain Machine Translation](https://md.research.elamur.ai/free/en/papers/ye-2026-translation-thought-difficulty-adaptive-reasoning/)
- [next → Translation-CoT: A Human-Inspired Chain-of-Thought Framework for Multilingual LLM Translation](https://md.research.elamur.ai/free/en/papers/prama-2026-translation-cot-human-inspired-chain/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/54/)

## References

18 references, 10 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Steven Y. Feng, Varun Gangal, Jason Wei, Sarath Chandar, Soroush Vosoughi, Teruko Mitamura, and Eduard Hovy. 2021. [A survey of data augmentation approaches for nlp](https://md.research.elamur.ai/free/en/papers/feng-2021-survey-data-augmentation-approaches-nlp/). Preprint, arXiv:2105.03075.
2. George Giannakopoulos, Jeff Kubina, John Conroy, Josef Steinberger, Benoit Favre, Mijail Kabadjov, Udo Kruschwitz, and Massimo Poesio. 2015. [find](https://scholar.google.com/scholar?q=George+Giannakopoulos%2C+Jeff+Kubina%2C+John+Conroy%2C+Josef+Steinberger%2C+Benoit+Favre%2C+Mijail+Kabadjov%2C+Udo+Kruschwitz%2C+and+Massimo+Poesio%2E+2015%2E)
3. MultiLing 2015: Multilingual summarization of single and multi-documents, on-line fora, and call-center conversations. In Proceedings of the 16th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 270–274, Prague, Czech Republic. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=MultiLing+2015%3A+Multilingual+summarization+of+single+and+multi%2Ddocuments%2C+on%2Dline+fora%2C+and+call%2Dcenter+conversations%2E+In+Proceedings+of+the+16th+Annual+Meeting+of+the+Special+Interest+Group+on+Discou)
4. Tahmid Hasan, Abhik Bhattacharjee, Md Saiful Islam, Kazi Mubasshir, Yuan-Fang Li, Yong-Bin Kang, M Sohel Rahman, and Rifat Shahriyar. 2021. Xl-sum: Large-scale multilingual abstractive summarization for 44 languages. Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 4… [find](https://scholar.google.com/scholar?q=Tahmid+Hasan%2C+Abhik+Bhattacharjee%2C+Md+Saiful+Islam%2C+Kazi+Mubasshir%2C+Yuan%2DFang+Li%2C+Yong%2DBin+Kang%2C+M+Sohel+Rahman%2C+and+Rifat+Shahriyar%2E+2021%2E+Xl%2Dsum%3A+Large%2Dscale+multilingual+abstractive+summarization+f)
5. Karl Moritz Hermann, Tomáš Kočiský, Edward Grefenstette, Lasse Espeholt, Will Kay, Mustafa Suleyman, and Phil Blunsom. 2015. [Teaching machines to read and comprehend](https://md.research.elamur.ai/free/en/papers/hermann-2015-teaching-machines-read-comprehend/). Preprint, arXiv:1506.03340.
6. Chin-Yew Lin. 2004. [ROUGE: A package for automatic evaluation of summaries](https://md.research.elamur.ai/free/en/papers/lin-2004-rouge-package-automatic-evaluation-summaries/). In Text Summarization Branches Out, pages 74–81, Barcelona, Spain. Association for Computational Linguistics.
7. Shashi Narayan, Shay B. Cohen, and Mirella Lapata. 2018. [Don’t give me the details, just the summary!](https://md.research.elamur.ai/free/en/papers/narayan-2018-don-t-give-me-details/) topic-aware convolutional neural networks for extreme summarization. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 1797–1807, Brussels, Belgium. As…
8. Arman Cohan, Franck Dernoncourt, Doo Soon Kim, Trung Bui, Seokhwan Kim, Walter Chang, and Nazli Goharian. 2018. [A discourse-aware attention model for abstractive summarization of long documents](https://md.research.elamur.ai/free/en/papers/cohan-2018-discourse-aware-attention-model-abstractive/). Preprint, arXiv:1804.05685.
9. NLLB Team, Marta R. Costa-jussà, James Cross, Onur Çelebi, Maha Elbayad, Kenneth Heafield, Kevin Heffernan, Kalbassi, and 1 others. 2022. No language left behind: Scaling human-centered machine translation. Preprint, arXiv:2207.04672. [find](https://scholar.google.com/scholar?q=NLLB+Team%2C+Marta+R%2E+Costa%2Djuss%C3%A0%2C+James+Cross%2C+Onur+%C3%87elebi%2C+Maha+Elbayad%2C+Kenneth+Heafield%2C+Kevin+Heffernan%2C+Kalbassi%2C+and+1+others%2E+2022%2E+No+language+left+behind%3A+Scaling+human%2Dcentered+machine+transl)
10. 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](https://md.research.elamur.ai/free/en/papers/conneau-2020-unsupervised-cross-lingual-representation-learning/). Preprint, arXiv:1911.02116.
11. Laura Pérez-Beltrachini, Mirella Lapata, and Ivan Vulić. 2020. Towards zero-shot cross-lingual abstractive sentence summarization. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 4253–4262. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Laura+P%C3%A9rez%2DBeltrachini%2C+Mirella+Lapata%2C+and+Ivan+Vulic%CC%81%2E+2020%2E+Towards+zero%2Dshot+cross%2Dlingual+abstractive+sentence+summarization%2E+In+Findings+of+the+Association+for+Computational+Linguistics%3A+EMNLP+)
12. Telmo Pires, Eva Schlinger, and Dan Garrette. 2019. [How multilingual is multilingual bert?](https://md.research.elamur.ai/free/en/papers/pires-2019-how-multilingual-is-multilingual-bert/) Preprint, arXiv:1906.01502.
13. Ricardo Rei, Craig Stewart, Ana C Farinha, and Alon Lavie. 2020. [COMET: A neural framework for MT evaluation](https://md.research.elamur.ai/free/en/papers/rei-2020-comet-neural-framework-mt-evaluation/). In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 2685–2702, Online. Association for Computational Linguistics.
14. Sebastian Ruder, Matthew E. Peters, Swabha Swayamdipta, and Thomas Wolf. 2019. [Transfer learning in natural language processing](https://md.research.elamur.ai/free/en/papers/ruder-2019-transfer-learning-natural-language-processing/). In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Tutorials, pages 15–18, Minneapolis, Minnesota. Assoc…
15. Thomas Scialom, Paul-Alexis Dray, Sylvain Lamprier, Benjamin Piwowarski, and Jacopo Staiano. 2020. [Mlsum: The multilingual summarization corpus](https://md.research.elamur.ai/free/en/papers/scialom-2020-mlsum-multilingual-summarization-corpus/). Preprint, arXiv:2004.14900.
16. Abigail See, Peter J. Liu, and Christopher D. Manning. 2017. Get to the point: Summarization with pointer-generator networks. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1073– 1083, Vancouver, Canada. Association for Compu… [find](https://scholar.google.com/scholar?q=Abigail+See%2C+Peter+J%2E+Liu%2C+and+Christopher+D%2E+Manning%2E+2017%2E+Get+to+the+point%3A+Summarization+with+pointer%2Dgenerator+networks%2E+In+Proceedings+of+the+55th+Annual+Meeting+of+the+Association+for+Computati)
17. Jasdeep Singh, Bryan McCann, Nitish Shirish Keskar, Caiming Xiong, and Richard Socher. 2019. Xlda: Cross-lingual data augmentation for natural language inference and question answering. Preprint, arXiv:1905.11471. [find](https://scholar.google.com/scholar?q=Jasdeep+Singh%2C+Bryan+McCann%2C+Nitish+Shirish+Keskar%2C+Caiming+Xiong%2C+and+Richard+Socher%2E+2019%2E+Xlda%3A+Cross%2Dlingual+data+augmentation+for+natural+language+inference+and+question+answering%2E+Preprint%2C+arXi)
18. Yuqing Tang, Chau Tran, Xian Li, Peng-Jen Chen, Naman Goyal, Vishrav Chaudhary, Jiatao Gu, and Angela Fan. 2020. Multilingual translation with extensible multilingual pretraining and finetuning. Preprint, arXiv:2008.00401. [find](https://scholar.google.com/scholar?q=Yuqing+Tang%2C+Chau+Tran%2C+Xian+Li%2C+Peng%2DJen+Chen%2C+Naman+Goyal%2C+Vishrav+Chaudhary%2C+Jiatao+Gu%2C+and+Angela+Fan%2E+2020%2E+Multilingual+translation+with+extensible+multilingual+pretraining+and+finetuning%2E+Prepr)

*Updated 2 November 2026*