---
title: "Learning Simplifications for Specific Target Audiences (2018)"
description: "The paper tackles text simplification (TS) for a specific reader, not a generic \"simpler\"… 59.83 BLEU. 25 references, cited by 76 papers here."
authors: ["Carolina Scarton", "Lucia Specia"]
year: 2018
venue: "Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)"
source: "https://aclanthology.org/P18-2113/"
doi: "10.18653/v1/p18-2113"
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/scarton-2018-learning-simplifications-specific-target-audiences/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/scarton-2018-learning-simplifications-specific-target-audiences/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2018](https://md.research.elamur.ai/free/en/papers/2018/page/4/) / Learning Simplifications for Specific Target Audiences

# Learning Simplifications for Specific Target Audiences

**Authors:** [Carolina Scarton](https://md.research.elamur.ai/free/en/authors/carolina-scarton/) and [Lucia Specia](https://md.research.elamur.ai/free/en/authors/lucia-specia/) · **Year:** 2018 · **Venue:** [Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)](https://md.research.elamur.ai/free/en/venues/acl/) ([ACL 2018](https://md.research.elamur.ai/free/en/venues/acl/2018/)) · **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/P18-2113/) · [PDF](https://aclanthology.org/P18-2113.pdf) · [DOI 10.18653/v1/p18-2113](https://doi.org/10.18653/v1/p18-2113) · [OpenAlex](https://openalex.org/W2798484540)

**Citations:** 59 citations (OpenAlex, 2026-10-14) · [76](https://md.research.elamur.ai/free/en/papers/scarton-2018-learning-simplifications-specific-target-audiences/cited-by/) in our library, of the 141,840 papers whose bibliographies we read

## Summary
The paper tackles text simplification (TS) for a specific reader, not a generic "simpler" output. The Newsela Article Corpus holds several professionally simplified versions of each news article, each aimed at a US school grade. Earlier work either ignored these grade labels or trained on restricted subsets of level pairs. The authors instead use all alignments, about 550K instance pairs, and borrow the multilingual MT trick of Johnson et al. (2017): an artificial token is prepended to each source sentence. The token encodes the target grade, the coarse simplification operation (identical, elaboration, splitting, joining), or both. Operations come either from gold alignments or from a Naive Bayes classifier. An OpenNMT LSTM encoder-decoder with attention is trained on the tagged data. The grade-aware models clearly beat a plain seq2seq baseline and the NTS system on BLEU and SARI, and their outputs land closer to the intended grade. The approach also handles zero-shot grade pairs. One model can therefore serve readers at many literacy levels.

## Key points
- Data: 550,644 aligned Newsela instance pairs, split 80/10/10. Alignments use Paetzold and Specia (2016) and link the original to every simplified version, plus simplified versions to each other (0-{1..4}, 1-{2,3,4}, etc.).
- Model: OpenNMT with 2-layer LSTMs, hidden size 500, dropout 0.3, Luong global attention with input-feeding, and 13 epochs. The checkpoint was chosen by development perplexity.
- Results (BLEU / SARI):
  - NTS: 61.60 / 33.40
  - s2s baseline: 61.78 / 33.72
  - s2s+to-grade: 62.91 / 41.04
  - s2s+to-grade+operation (gold): 64.78 / 45.41
  - Predicted operations only: 59.83 BLEU, which is below the baseline. Combining them with the grade token recovers to 61.48 / 40.56.
- Flesch-Kincaid Grade Level of the grade-tagged models' outputs is consistently nearer the requested grade than the baseline's.
- Zero-shot: models were trained without a given grade pair. For ⟨12,4⟩ they reach 50.85 SARI versus 37.56 for the baseline, and for ⟨12,7⟩ they also beat the baseline. For the close pair ⟨6,5⟩, all systems perform about the same.

## Interesting ideas
- **Control tokens as conditioning:** A single prepended tag lets one seq2seq model produce different outputs for different audiences, with no architecture change. The same trick could steer register, dialect, or formality in other generation tasks.
- **Use "conflicting" data instead of discarding it:** When the same input maps to several valid outputs, labelling the condition turns noise into signal. This allows the full corpus to be used rather than filtered subsets.
- **Decompose the hard decision:** Predicting a coarse operation type first is easier than performing the rewrite, and it guides the generator. The gold-vs-predicted gap shows how much a better classifier could add.
- **Zero-shot via held-out condition pairs:** The authors remove one source–target grade pair from training while keeping the target grade in other pairs. This is a clean way to test whether conditioning really generalises.
- **Audience-aware automatic evaluation:** A readability formula that outputs grade levels is compared against the requested grade. This offers a cheap substitute when human judges at each target level are impractical.

*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 Sheffield](https://md.research.elamur.ai/free/en/universities/university-of-sheffield/) — University, Sheffield, United Kingdom · 76 works · 20,808 citations

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 9,085 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 8,888 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 9,296 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 9,206 works

## Cite

Cite as: Carolina Scarton and Lucia Specia. 2018. Learning Simplifications for Specific Target Audiences. Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers).

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

```bibtex
@inproceedings{scarton2018learning,
  title = {{Learning Simplifications for Specific Target Audiences}},
  author = {Carolina Scarton and Lucia Specia},
  booktitle = {Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)},
  year = {2018},
  doi = {10.18653/v1/p18-2113},
  url = {https://doi.org/10.18653/v1/p18-2113}
}
```

- [← previous Extending a Parser to Distant Domains Using a Few Dozen Partially Annotated Examples](https://md.research.elamur.ai/free/en/papers/joshi-2018-extending-parser-distant-domains-few/)
- [next → Semantic Structural Evaluation for Text Simplification](https://md.research.elamur.ai/free/en/papers/sulem-2018-semantic-structural-evaluation-text-simplification/)
- [↑ back to papers of 2018](https://md.research.elamur.ai/free/en/papers/2018/page/4/)

## References

25 references, 15 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. for Computational Linguistics, Vancouver, Canada, pages 85–91. — [Exploring Neural Text Simplification Models](https://md.research.elamur.ai/free/en/papers/nisioi-2017-exploring-neural-text-simplification-models/) [http://aclweb.org/anthology/P17-2014](http://aclweb.org/anthology/P17-2014). [↗](http://aclweb.org/anthology/P17-2014)
2. Fernando Alva-Manchego, Joachim Bingel, Gustavo Paetzold, Carolina Scarton, and Lucia Specia. 2017. [Learning how to simplify from explicit labeling of complex-simplified text pairs](https://md.research.elamur.ai/free/en/papers/manchego-2017-learning-how-simplify-explicit-labeling/). In Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers). As…
3. Gustavo Paetzold and Lucia Specia. 2013. Text simplification as tree transduction. In Proceedings of the 9th Brazilian Symposium in Information and Human Language Technology. Fortaleza, Brazil, STIL, pages 116–125. [http://aclweb.org/anthology/W13-4813](http://aclweb.org/anthology/W13-4813). [↗](http://aclweb.org/anthology/W13-4813)
4. Gustavo Henrique Paetzold. 2016. Lexical Simplification for Non-Native English Speakers. Ph.D. thesis, University of Sheffield, Sheffield, UK. [http://etheses.whiterose.ac.uk/15332/](http://etheses.whiterose.ac.uk/15332/). [↗](http://etheses.whiterose.ac.uk/15332/)
5. Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. 2015. [Neural machine translation by jointly learning to align and translate](https://md.research.elamur.ai/free/en/papers/bahdanau-2014-neural-machine-translation-jointly-learning/). In Proceedings of the 3rd International Conference on Learning Representations. San Diego, CA, ICLR ’15. [https://arxiv.org/pdf/1409.0473.pdf](https://arxiv.org/pdf/1409.0473.pdf). [↗](https://arxiv.org/pdf/1409.0473.pdf)
6. William Coster and David Kauchak. 2011a. [Learning to simplify sentences using wikipedia](https://md.research.elamur.ai/free/en/papers/coster-2011-learning-simplify-sentences-wikipedia/). In Proceedings of the Workshop on Monolingual Text-To-Text Generation. ACL, Portland, Oregon, MTTG ’11, pages 1–9. [http://dl.acm.org/citation.cfm?id=2107679.2107680](http://dl.acm.org/citation.cfm?id=2107679.2107680). [↗](http://dl.acm.org/citation.cfm?id=2107679.2107680)
7. William Coster and David Kauchak. 2011b. [Simple english wikipedia: A new text simplification task](https://md.research.elamur.ai/free/en/papers/coster-2011-simple-english-wikipedia-new-text/). In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies: Short Papers - Volume 2. Association for Computational Linguistics, Stroudsburg,…
8. Melvin Johnson, Mike Schuster, Quoc V. Le, Maxim Krikun, Yonghui Wu, Zhifeng Chen, Nikhil Thorat, Fernanda Viégas, Martin Wattenberg, Greg Corrado, Macduff Hughes, and Jeffrey Dean. 2017. Google’s Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation. Transactions of the As… [find](https://scholar.google.com/scholar?q=Melvin+Johnson%2C+Mike+Schuster%2C+Quoc+V%2E+Le%2C+Maxim+Krikun%2C+Yonghui+Wu%2C+Zhifeng+Chen%2C+Nikhil+Thorat%2C+Fernanda+Vie%CC%81gas%2C+Martin+Wattenberg%2C+Greg+Corrado%2C+Macduff+Hughes%2C+and+Jeffrey+Dean%2E+2017%2E+Google%E2%80%99s+Mu)
9. Gustavo Henrique Paetzold and Lucia Specia. 2016. Vicinity-driven paragraph and sentence alignment for comparable corpora. CoRR abs/1612.04113. http://arxiv.org/abs/1612.04113. — [arXiv:1612.04113](https://arxiv.org/abs/1612.04113) [↗](http://arxiv.org/abs/1612.04113)
10. Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. [Bleu: A method for automatic evaluation of machine translation](https://md.research.elamur.ai/free/en/papers/papineni-2002-bleu-method-automatic-evaluation-machine/). In Proceedings of the 40th Annual Meeting on Association for Computational Linguistics. ACL, Philadelphia, Pennsylvania, ACL ’02, pages 311–318. https://doi.org/10.3115/…
11. 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 . [find](https://scholar.google.com/scholar?q=F%2E+Pedregosa%2C+G%2E+Varoquaux%2C+A%2E+Gramfort%2C+V%2E+Michel%2C+B%2E+Thirion%2C+O%2E+Grisel%2C+M%2E+Blondel%2C+P%2E+Prettenhofer%2C+R%2E+Weiss%2C+V%2E+Dubourg%2C+J%2E+Vanderplas%2C+A%2E+Passos%2C+D%2E+Cournapeau%2C+M%2E+Brucher%2C+M%2E+Perrot%2C+and+E%2E+Duc)
12. Carolina Scarton, Gustavo Henrique Paetzold, and Lucia Specia. 2018a. SimPA: A Sentence-Level Simplification Corpus for the Public Administration Domain. In Proceedings of the Eleventh International Conference on Language Resources and Evaluation. European Language Resources Association (ELRA), Miya… [find](https://scholar.google.com/scholar?q=Carolina+Scarton%2C+Gustavo+Henrique+Paetzold%2C+and+Lucia+Specia%2E+2018a%2E+SimPA%3A+A+Sentence%2DLevel+Simplification+Corpus+for+the+Public+Administration+Domain%2E+In+Proceedings+of+the+Eleventh+International+C)
13. Thang Luong, Hieu Pham, and Christopher D. Manning. 2015. [Effective approaches to attention-based neural machine translation](https://md.research.elamur.ai/free/en/papers/luong-2015-effective-approaches-attention-based-neural/). In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Lisbon, Portugal, pages 1412– 1421. http…
14. Carolina Scarton, Gustavo Henrique Paetzold, and Lucia Specia. 2018b. Text Simplification from Professionally Produced Corpora. In Proceedings of the Eleventh International Conference on Language Resources and Evaluation. European Language Resources Association (ELRA), Miyazaki, Japan, pages 3504–35… [find](https://scholar.google.com/scholar?q=Carolina+Scarton%2C+Gustavo+Henrique+Paetzold%2C+and+Lucia+Specia%2E+2018b%2E+Text+Simplification+from+Professionally+Produced+Corpora%2E+In+Proceedings+of+the+Eleventh+International+Conference+on+Language+Reso)
15. Shashi Narayan and Claire Gardent. 2014. [Hybrid simplification using deep semantics and machine translation](https://md.research.elamur.ai/free/en/papers/narayan-2014-hybrid-simplification-deep-semantics-machine/). In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics, Baltimore, Maryland, pages 435–…
16. Carolina Scarton, Alessio Palmero Aprosio, Sara Tonelli, Tamara Martı́n Wanton, and Lucia Specia. 2017. MUSST: A Multilingual Syntactic Simplification Tool. In Proceedings of the Eighth International Joint Conference on Natural Language Processing (System Demonstrations). Asian Federation of Natural… [find](https://scholar.google.com/scholar?q=Carolina+Scarton%2C+Alessio+Palmero+Aprosio%2C+Sara+Tonelli%2C+Tamara+Mart%C4%B1%CC%81n+Wanton%2C+and+Lucia+Specia%2E+2017%2E+MUSST%3A+A+Multilingual+Syntactic+Simplification+Tool%2E+In+Proceedings+of+the+Eighth+International+)
17. Sergiu Nisioi, Sanja Štajner, Simone Paolo Ponzetto, and Liviu P. Dinu. 2017. [Exploring neural text simplification models](https://md.research.elamur.ai/free/en/papers/nisioi-2017-exploring-neural-text-simplification-models/). In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers).
18. Association Advaith Siddharthan. 2011. Text simplification using typed dependencies: A comparison of the robustness of different generation strategies. In Proceedings of the 13th European Workshop on Natural Language Generation. Association for Computational Linguistics, Stroudsburg, PA, USA, ENLG ’… [find](https://scholar.google.com/scholar?q=Association+Advaith+Siddharthan%2E+2011%2E+Text+simplification+using+typed+dependencies%3A+A+comparison+of+the+robustness+of+different+generation+strategies%2E+In+Proceedings+of+the+13th+European+Workshop+on+)
19. Sanja Štajner, Marc Franco-Salvador, Simone Paolo Ponzetto, Paolo Rosso, and Heiner Stuckenschmidt. 2017. Sentence alignment methods for improving text simplification systems. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). Associ… [find](https://scholar.google.com/scholar?q=Sanja+S%CC%8Ctajner%2C+Marc+Franco%2DSalvador%2C+Simone+Paolo+Ponzetto%2C+Paolo+Rosso%2C+and+Heiner+Stuckenschmidt%2E+2017%2E+Sentence+alignment+methods+for+improving+text+simplification+systems%2E+In+Proceedings+of+the+5)
20. Kristian Woodsend and Mirella Lapata. 2011. [Learning to Simplify Sentences with Quasi-Synchronous Grammar and Integer Programming](https://md.research.elamur.ai/free/en/papers/woodsend-2011-learning-simplify-sentences-quasi-synchronous/). In Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Edinburgh, Scotland, UK., pages 409…
21. Sander Wubben, Antal van den Bosch, and Emiel Krahmer. 2012. [Sentence simplification by monolingual machine translation](https://md.research.elamur.ai/free/en/papers/wubben-2012-sentence-simplification-monolingual-machine-translation/). In Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Long Papers - Volume 1. Association for Computational Linguistics, Stroudsburg, PA, USA…
22. Wei Xu, Chris Callison-Burch, and Courtney Napoles. 2015. [Problems in current text simplification research: New data can help](https://md.research.elamur.ai/free/en/papers/xu-2015-problems-current-text-simplification-research/). Transactions of the Association for Computational Linguistics 3:283–297. [http://www.aclweb.org/anthology/Q15-1021](http://www.aclweb.org/anthology/Q15-1021). [↗](http://www.aclweb.org/anthology/Q15-1021)
23. Wei Xu, Courtney Napoles, Ellie Pavlick, Quanze Chen, and Chris Callison-Burch. 2016. [Optimizing statistical machine translation for text simplification](https://md.research.elamur.ai/free/en/papers/xu-2016-optimizing-statistical-machine-translation-text/). Transactions of the Association for Computational Linguistics 4:401–415. [http://www.aclweb.org/anthology/Q16-1029](http://www.aclweb.org/anthology/Q16-1029). [↗](http://www.aclweb.org/anthology/Q16-1029)
24. Xingxing Zhang and Mirella Lapata. 2017. [Sentence simplification with deep reinforcement learning](https://md.research.elamur.ai/free/en/papers/zhang-2017-sentence-simplification-deep-reinforcement-learning/). In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Copenhagen, Denmark, pages 595–605. [https://www.aclweb.org/antholog…](https://www.aclweb.org/antholog…) [↗](https://www.aclweb.org/antholog…)
25. Zhemin Zhu, Delphine Bernhard, and Iryna Gurevych. 2010. [A monolingual tree-based translation model for sentence simplification](https://md.research.elamur.ai/free/en/papers/zhu-2010-monolingual-tree-based-translation-model/). In Proceedings of the 23rd International Conference on Computational Linguistics. Association for Computational Linguistics, Stroudsburg, PA, USA, COLING ’10, pages 1353–1…

*Updated 24 October 2026*