---
title: "Supervised and Unsupervised Neural Approaches — Martinc 2021"
description: "Estimating how difficult a text is to read has usually relied on simple formulas based on sentence length, word length and word lists, or on classifiers…"
authors: ["Matej Martinc", "Senja Pollak", "Marko Robnik-Šikonja"]
year: 2021
venue: "Computational Linguistics"
source: "https://aclanthology.org/2021.cl-1.6/"
doi: "10.1162/coli_a_00398"
licence: "CC BY-NC-ND 4.0 (Computational Linguistics, MIT Press)"
licence_url: "https://creativecommons.org/licenses/by-nc-nd/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/martinc-2021-supervised-unsupervised-neural-approaches-text/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/martinc-2021-supervised-unsupervised-neural-approaches-text/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2021](https://md.research.elamur.ai/free/en/papers/2021/page/5/) / Supervised and Unsupervised Neural Approaches to Text Readability

# Supervised and Unsupervised Neural Approaches to Text Readability

**Authors:** [Matej Martinc](https://md.research.elamur.ai/free/en/authors/matej-martinc/), [Senja Pollak](https://md.research.elamur.ai/free/en/authors/senja-pollak/), Marko Robnik-Šikonja · **Year:** 2021 · **Venue:** Computational Linguistics · **Licence:** [CC BY-NC-ND 4.0 (Computational Linguistics, MIT Press)](https://creativecommons.org/licenses/by-nc-nd/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2021.cl-1.6/) · [PDF](https://aclanthology.org/2021.cl-1.6.pdf) · [DOI 10.1162/coli\_a\_00398](https://doi.org/10.1162/coli_a_00398) · [OpenAlex](https://openalex.org/W2964941017)

**Citations:** 114 citations (openalex-snapshot · 2026-10-14) · [76](#cited-by) in our library, of the 140884 papers whose bibliographies we read

## Summary
Estimating how difficult a text is to read has usually relied on simple formulas based on sentence length, word length and word lists, or on classifiers built from large sets of hand-crafted features. Those classifiers need labeled data, which is scarce, and they generalize poorly to other corpora and languages. The authors explore neural alternatives for English and for Slovenian, a morphologically rich language with far fewer resources.

In the unsupervised setting, they derive readability from neural language model statistics. This requires only unlabeled text from the target domain. They also propose a new score, RSRS (ranked sentence readability score), which correlates well with gold readability levels and can be adapted to a particular task, dataset and language.

In the supervised setting, they systematically compare recurrent networks, hierarchical attention networks (HAN) and BERT-based transfer learning on four labeled corpora. Document length turns out to be the deciding factor: HAN is best on long documents, while BERT leads on shorter ones.

The work matters because it gives a cross-lingual baseline that needs no feature engineering. It also shows where each neural architecture fits best.

## Key points
- The unsupervised approach uses neural language models and introduces RSRS. It transfers across languages (English and Slovenian) and needs no labeled training set.
- The supervised comparison covers RNN, HAN and transfer learning (BERT) on four gold-standard corpora: WeeBit, OneStopEnglish, Newsela and Slovenian SB.
- On OneStopEnglish, HAN reaches 78.72% accuracy. A feature-based classifier with 155 hand-crafted features (Vajjala and Lučić 2018) scores 78.13%, and plain 2–5 character n-grams reach 77.25%. The neural gain is therefore modest, and it comes at a cost in interpretability.
- BERT achieves clearly better QWK on the shorter-document, non-parallel corpora (WeeBit, Slovenian SB). On Newsela and OneStopEnglish, most texts must be cut to BERT's 512-token limit.
- Planned future work includes:
  - Longformer and Linformer for long documents.
  - Explaining predictions with SHAP or attention.
  - Neural ensembles.
  - Cross-corpus, cross-genre and cross-language evaluation.

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

Fields: [Natural language processing](https://md.research.elamur.ai/free/en/shelves/nlp/)

## Cited by

Cited by

76 papers of our library cite it (of the 140884 whose bibliographies we read); 2 of them have a page here, 74 not yet.

- [Translation as Augmentation: Effect of Translated Data on Assessment of Difficulty](https://md.research.elamur.ai/free/en/papers/wu-2026-translation-as-augmentation-effect-translated/)
- [Let's Simplify Step by Step: Guiding LLM Towards Multilingual Unsupervised Proficiency-Controlled Sentence Simplification](https://md.research.elamur.ai/free/en/papers/zhang-2026-let-s-simplify-step-step/)

## Cite

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

```bibtex
@article{martinc2021supervised,
  title = {{Supervised and Unsupervised Neural Approaches to Text Readability}},
  author = {Martinc, Matej and Pollak, Senja and Robnik-Šikonja, Marko},
  journal = {Computational Linguistics},
  year = {2021},
  doi = {10.1162/coli\_a\_00398},
  url = {https://doi.org/10.1162/coli_a_00398}
}
```

- [← previous Superbizarre Is Not Superb: Derivational Morphology Improves BERT's Interpretation of Complex Words](https://md.research.elamur.ai/free/en/papers/lex-2021-hofmann-superbizarre-derivational/)
- [next → Surface Form Competition: Why the Highest Probability Answer Isn't Always Right](https://md.research.elamur.ai/free/en/papers/holtzman-2021-surface-form-competition-why-highest/)
- [↑ back to papers of 2021](https://md.research.elamur.ai/free/en/papers/2021/page/5/)

## References

39 references, 11 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Anderson, Jonathan. 1981. Analysing the readability of English and non-English texts in the classroom with LIX. In Seventh Australian Reading Association Conference, pages 1–12, Darwin. [find](https://scholar.google.com/scholar?q=Anderson%2C+Jonathan%2E+1981%2E+Analysing+the+readability+of+English+and+non%2DEnglish+texts+in+the+classroom+with+LIX%2E+In+Seventh+Australian+Reading+Association+Conference%2C+pages+1%E2%80%9312%2C+Darwin%2E)
2. Azpiazu, Ion Madrazo and Maria Soledad Pera. 2019. Multiattentive recurrent neural network architecture for multilingual readability assessment. Transactions of the Association for Computational Linguistics, 7:421–436. DOI: https://doi.org/10 .1162/tacl a 00278 Bahdanau, Dzmitry, Kyunghyun Cho, and… [find](https://scholar.google.com/scholar?q=Azpiazu%2C+Ion+Madrazo+and+Maria+Soledad+Pera%2E+2019%2E+Multiattentive+recurrent+neural+network+architecture+for+multilingual+readability+assessment%2E+Transactions+of+the+Association+for+Computational+Lingu)
3. Bai, Shaojie, J. Zico Kolter, and Vladlen Koltun. 2018. An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv preprint arXiv:1803.01271. — [arXiv:1803.01271](https://arxiv.org/abs/1803.01271) [find](https://scholar.google.com/scholar?q=Bai%2C+Shaojie%2C+J%2E+Zico+Kolter%2C+and+Vladlen+Koltun%2E+2018%2E+An+empirical+evaluation+of+generic+convolutional+and+recurrent+networks+for+sequence+modeling%2E+arXiv+preprint+arXiv%3A1803%2E01271%2E+%E2%80%94+%5BarXiv%3A1803%2E01)
4. Beltagy, Iz, Matthew E. Peters, and Arman Cohan. 2020. Longformer: The long-document transformer. arXiv preprint arXiv:2004.05150. [find](https://scholar.google.com/scholar?q=Beltagy%2C+Iz%2C+Matthew+E%2E+Peters%2C+and+Arman+Cohan%2E+2020%2E+Longformer%3A+The+long%2Ddocument+transformer%2E+arXiv+preprint+arXiv%3A2004%2E05150%2E)
5. Bengio, Yoshua, Patrice Simard, and Paolo Frasconi. 1994. Learning long-term dependencies with gradient descent is difficult. IEEE Transactions on Neural Networks, 5(2):157–166. DOI: https://doi.org/10.1109/72.279181, PMID: 18267787 Bird, Steven and Edward Loper. 2004. NLTK: The natural language to… [↗](https://doi.org/10.1109/72.279181)
6. Collins-Thompson, Kevyn. 2014. Computational assessment of text readability: A survey of current and future research. ITL-International Journal of Applied Linguistics, 165(2):97–135. DOI: https://doi.org/10.1075/itl.165.2.01col Collobert, Ronan, Jason Weston, Léon Bottou, Michael Karlen, Koray Kav… — [doi:10.1075/itl.165.2.01col](https://doi.org/10.1075/itl.165.2.01col) [↗](https://doi.org/10.1075/itl.165.2.01col)
7. Education Committee. Modern Languages Division. 2001. Common European Framework of Reference for Languages: Learning, Teaching, Assessment. [find](https://scholar.google.com/scholar?q=Education+Committee%2E+Modern+Languages+Division%2E+2001%2E+Common+European+Framework+of+Reference+for+Languages%3A+Learning%2C+Teaching%2C+Assessment%2E)
8. Cambridge University Press. Crossley, Scott A., Stephen Skalicky, Mihai Dascalu, Danielle S. McNamara, and Kristopher Kyle. 2017. Predicting text comprehension, processing, and familiarity in adult readers: New approaches to readability formulas. Discourse Processes, 54(5-6):340–359. DOI: https://do… [find](https://scholar.google.com/scholar?q=Cambridge+University+Press%2E+Crossley%2C+Scott+A%2E%2C+Stephen+Skalicky%2C+Mihai+Dascalu%2C+Danielle+S%2E+McNamara%2C+and+Kristopher+Kyle%2E+2017%2E+Predicting+text+comprehension%2C+processing%2C+and+familiarity+in+adult+re)
9. Davison, Alice and Robert N. Kantor. 1982. On the failure of readability formulas to define readable texts: A case study from adaptations. Reading Research Quarterly, pages 187–209. DOI: https://doi.org/10.2307/747483 Deutsch, Tovly, Masoud Jasbi, and Stuart Shieber. 2020. Linguistic features for r… [↗](https://doi.org/10.2307/747483)
10. Feng, Lijun. 2008. Text simplification: A survey, The City University of New York. Feng, Lijun, Noémie Elhadad, and Matt Huenerfauth. 2009. Cognitively motivated features for readability assessment. In Proceedings of the 12th Conference of the European Chapter of the ACL (EACL 2009), pages 229–237,… [find](https://scholar.google.com/scholar?q=Feng%2C+Lijun%2E+2008%2E+Text+simplification%3A+A+survey%2C+The+City+University+of+New+York%2E+Feng%2C+Lijun%2C+Noe%CC%81mie+Elhadad%2C+and+Matt+Huenerfauth%2E+2009%2E+Cognitively+motivated+features+for+readability+assessment%2E+)
11. Filighera, Anna, Tim Steuer, and Christoph Rensing. 2019. Automatic text difficulty estimation using embeddings and neural networks. In European Conference on Technology Enhanced Learning, pages 335–348, Delft. DOI: https://doi.org/10.1007/978-3-030-29736-7 25 Flor, Michael, Beata Beigman Klebanov,… — [doi:10.1007/978-3-030-29736-7](https://doi.org/10.1007/978-3-030-29736-7) [↗](https://doi.org/10.1007/978-3-030-29736-7)
12. Goldberg, Yoav and Jon Orwant. 2013. A data set of syntactic-ngrams over time from a very large corpus of English books. In Second Joint Conference on Lexical and Computational Semantics, pages 241–247, Atlanta, GA. [find](https://scholar.google.com/scholar?q=Goldberg%2C+Yoav+and+Jon+Orwant%2E+2013%2E+A+data+set+of+syntactic%2Dngrams+over+time+from+a+very+large+corpus+of+English+books%2E+In+Second+Joint+Conference+on+Lexical+and+Computational+Semantics%2C+pages+241%E2%80%9324)
13. Goodfellow, Ian, Yoshua Bengio, and Aaron Courville. 2016. [find](https://scholar.google.com/scholar?q=Goodfellow%2C+Ian%2C+Yoshua+Bengio%2C+and+Aaron+Courville%2E+2016%2E)
14. Deep Learning. MIT Press. Gunning, Robert. 1952. The Technique of Clear Writing. [find](https://scholar.google.com/scholar?q=Deep+Learning%2E+MIT+Press%2E+Gunning%2C+Robert%2E+1952%2E+The+Technique+of+Clear+Writing%2E)
15. McGraw-Hill, New York. Halliday, Michael Alexander Kirkwood and Ruqaiya Hasan. 1976. Cohesion in English. Routledge. Jawahar, Ganesh, Benoı̂t Sagot, and Djamé Seddah. 2019. What does BERT learn about the structure of language? In Proceedings of the 57th Annual Meeting of the Association for Computa… [find](https://scholar.google.com/scholar?q=McGraw%2DHill%2C+New+York%2E+Halliday%2C+Michael+Alexander+Kirkwood+and+Ruqaiya+Hasan%2E+1976%2E+Cohesion+in+English%2E+Routledge%2E+Jawahar%2C+Ganesh%2C+Beno%C4%B1%CC%82t+Sagot%2C+and+Djame%CC%81+Seddah%2E+2019%2E+What+does+BERT+learn+about) [our card](https://md.research.elamur.ai/free/en/papers/jawahar-2019-what-does-bert-learn-about/)
16. Kim, Yoon, Yacine Jernite, David Sontag, and Alexander M. Rush. 2016. Character-aware neural language models. In AAAI, pages 2741–2749, Phoenix, AZ. [find](https://scholar.google.com/scholar?q=Kim%2C+Yoon%2C+Yacine+Jernite%2C+David+Sontag%2C+and+Alexander+M%2E+Rush%2E+2016%2E+Character%2Daware+neural+language+models%2E+In+AAAI%2C+pages+2741%E2%80%932749%2C+Phoenix%2C+AZ%2E) [our card](https://md.research.elamur.ai/free/en/papers/kim-2015-character-aware-neural-language-models/)
17. Kincaid, J. Peter, Robert P. Fishburne Jr, Richard L. Rogers, and Brad S. Chissom. 1975. Derivation of New Readability Formulas (Automated Readability Index, Fog Count and Flesch Reading Ease Formula) for Navy Enlisted Personnel. Institute for Simulation and Training, University of Central Florida. [find](https://scholar.google.com/scholar?q=Kincaid%2C+J%2E+Peter%2C+Robert+P%2E+Fishburne+Jr%2C+Richard+L%2E+Rogers%2C+and+Brad+S%2E+Chissom%2E+1975%2E+Derivation+of+New+Readability+Formulas+%28Automated+Readability+Index%2C+Fog+Count+and+Flesch+Reading+Ease+Formula%29)
18. Kudo, Taku and John Richardson. 2018. Sentencepiece: A simple and language independent subword tokenizer and detokenizer for neural text processing. arXiv preprint arXiv:1808.06226. DOI: https://doi.org/10.18653/v1/D18 -2012, PMID: 29382465 Landauer, Thomas K. 2011. Pearson’s text complexity measure… [↗](https://doi.org/10.18653/v1/D18) [our card](https://md.research.elamur.ai/free/en/papers/kudo-2018-sentencepiece-simple-language-independent-subword/)
19. Lundberg, Scott M. and Su-In Lee. 2017. A unified approach to interpreting model predictions. In Advances in Neural Information Processing Systems, pages 4768–4777, Long Beach, CA. [find](https://scholar.google.com/scholar?q=Lundberg%2C+Scott+M%2E+and+Su%2DIn+Lee%2E+2017%2E+A+unified+approach+to+interpreting+model+predictions%2E+In+Advances+in+Neural+Information+Processing+Systems%2C+pages+4768%E2%80%934777%2C+Long+Beach%2C+CA%2E) [our card](https://md.research.elamur.ai/free/en/papers/lundberg-2017-unified-approach-interpreting-model-predictions/)
20. Ma, Yi, Eric Fosler-Lussier, and Robert Lofthus. 2012. Ranking-based readability assessment for early primary children’s literature. In Proceedings of the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 548–552, Montr… [find](https://scholar.google.com/scholar?q=Ma%2C+Yi%2C+Eric+Fosler%2DLussier%2C+and+Robert+Lofthus%2E+2012%2E+Ranking%2Dbased+readability+assessment+for+early+primary+children%E2%80%99s+literature%2E+In+Proceedings+of+the+2012+Conference+of+the+North+American+Chapter)
21. Madnani, Nitin and Aoife Cahill. 2018. Automated scoring: Beyond natural language processing. In Proceedings of the 27th International Conference on Computational Linguistics, pages 1099–1109, Santa Fe, NM. [find](https://scholar.google.com/scholar?q=Madnani%2C+Nitin+and+Aoife+Cahill%2E+2018%2E+Automated+scoring%3A+Beyond+natural+language+processing%2E+In+Proceedings+of+the+27th+International+Conference+on+Computational+Linguistics%2C+pages+1099%E2%80%931109%2C+Santa+F)
22. Madrazo Azpiazu, Ion and Maria Soledad Pera. 2020. Is crosslingual readability assessment possible? Journal of the Association for Information Science and Technology, 71(6):644–656. DOI: https://doi.org/10.1002/asi.24293 McLaughlin, G. Harry. 1969. SMOG grading—a new readability formula. Journal of… — [doi:10.1002/asi.24293](https://doi.org/10.1002/asi.24293) [↗](https://doi.org/10.1002/asi.24293)
23. Mikolov, Tomas, Ilya Sutskever, Kai Chen, Greg S. Corrado, and Jeff Dean. 2013. Distributed representations of words and phrases and their compositionality. In Advances in Neural Information Processing Systems, pages 3111–3119, Florence. [find](https://scholar.google.com/scholar?q=Mikolov%2C+Tomas%2C+Ilya+Sutskever%2C+Kai+Chen%2C+Greg+S%2E+Corrado%2C+and+Jeff+Dean%2E+2013%2E+Distributed+representations+of+words+and+phrases+and+their+compositionality%2E+In+Advances+in+Neural+Information+Processin)
24. Mohammadi, Hamid and Seyed Hossein Khasteh. 2019. Text as environment: A deep reinforcement learning text readability assessment model. arXiv preprint arXiv:1912.05957. — [arXiv:1912.05957](https://arxiv.org/abs/1912.05957) [find](https://scholar.google.com/scholar?q=Mohammadi%2C+Hamid+and+Seyed+Hossein+Khasteh%2E+2019%2E+Text+as+environment%3A+A+deep+reinforcement+learning+text+readability+assessment+model%2E+arXiv+preprint+arXiv%3A1912%2E05957%2E+%E2%80%94+%5BarXiv%3A1912%2E05957%5D%28https%3A%2F%2Far)
25. Nadeem, Farah and Mari Ostendorf. 2018. Estimating linguistic complexity for science texts. In Proceedings of the Thirteenth Workshop on Innovative Use of NLP for Building Educational Applications, pages 45–55, New Orleans, LA. DOI: https://doi.org/10.18653/v1/W18 -0505 Napolitano, Diane, Kathleen M… [↗](https://doi.org/10.18653/v1/W18)
26. Petersen, Sarah E. and Mari Ostendorf. 2009. A machine learning approach to reading level assessment. Computer Speech & Language, 23(1):89–106. DOI: https://doi.org/10.1016/j.csl.2008.04.003 Pitler, Emily and Ani Nenkova. 2008. Revisiting readability: A unified framework for predicting text quality… [↗](https://doi.org/10.1016/j.csl.2008.04.003) [our card](https://md.research.elamur.ai/free/en/papers/pitler-2008-revisiting-readability-unified-framework-predicting/)
27. Schwarm, Sarah E. and Mari Ostendorf. 2005. Reading level assessment using support vector machines and statistical language models. In Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics, pages 523–530, Ann Arbor, MI. DOI: [https://doi.org](https://doi.org) /10.3115/1219840.1219905… [↗](https://doi.org) [our card](https://md.research.elamur.ai/free/en/papers/schwarm-2005-reading-level-assessment-support-vector/)
28. Sheehan, Kathleen M., Irene Kostin, Yoko Futagi, and Michael Flor. 2010. Generating automated text complexity classifications that are aligned with targeted text complexity standards. ETS Research Report Series, 2010(2):i–44. DOI: https://doi.org/10.1002/j.2333-8504.2010 .tb02235.x Sheehan, Kathlee… — [doi:10.1002/j.2333-8504.2010](https://doi.org/10.1002/j.2333-8504.2010) [↗](https://doi.org/10.1002/j.2333-8504.2010)
29. Vajjala, Sowmya and Detmar Meurers. 2012. On improving the accuracy of readability classification using insights from second language acquisition. In Proceedings of the Seventh Workshop on Building Educational Applications Using NLP, pages 163–173, Montreal. [find](https://scholar.google.com/scholar?q=Vajjala%2C+Sowmya+and+Detmar+Meurers%2E+2012%2E+On+improving+the+accuracy+of+readability+classification+using+insights+from+second+language+acquisition%2E+In+Proceedings+of+the+Seventh+Workshop+on+Building+Ed) [our card](https://md.research.elamur.ai/free/en/papers/vajjala-2012-improving-accuracy-readability-classification-insights/)
30. Van Dijk, Teun Adrianus. 1977. Text and Context: Explorations in the Semantics and Pragmatics of Discourse. [find](https://scholar.google.com/scholar?q=Van+Dijk%2C+Teun+Adrianus%2E+1977%2E+Text+and+Context%3A+Explorations+in+the+Semantics+and+Pragmatics+of+Discourse%2E)
31. Longman London. Vaswani, Ashish, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Advances in Neural Information Processing Systems, pages 5998–6008, Long Beach, CA. [find](https://scholar.google.com/scholar?q=Longman+London%2E+Vaswani%2C+Ashish%2C+Noam+Shazeer%2C+Niki+Parmar%2C+Jakob+Uszkoreit%2C+Llion+Jones%2C+Aidan+N%2E+Gomez%2C+%C5%81ukasz+Kaiser%2C+and+Illia+Polosukhin%2E+2017%2E+Attention+is+all+you+need%2E+In+Advances+in+Neural+In)
32. Wang, Sinong, Belinda Li, Madian Khabsa, Han Fang, and Hao Ma. 2020. Linformer: Self-attention with linear complexity. arXiv preprint arXiv:2006.04768. [find](https://scholar.google.com/scholar?q=Wang%2C+Sinong%2C+Belinda+Li%2C+Madian+Khabsa%2C+Han+Fang%2C+and+Hao+Ma%2E+2020%2E+Linformer%3A+Self%2Dattention+with+linear+complexity%2E+arXiv+preprint+arXiv%3A2006%2E04768%2E)
33. Wang, Ziyu, Tom Schaul, Matteo Hessel, Hado Hasselt, Marc Lanctot, and Nando Freitas. 2016. Dueling network architectures for deep reinforcement learning. In International Conference on Machine Learning, pages 1995–2003, New York. [find](https://scholar.google.com/scholar?q=Wang%2C+Ziyu%2C+Tom+Schaul%2C+Matteo+Hessel%2C+Hado+Hasselt%2C+Marc+Lanctot%2C+and+Nando+Freitas%2E+2016%2E+Dueling+network+architectures+for+deep+reinforcement+learning%2E+In+International+Conference+on+Machine+Learni)
34. Williams, Geoffrey. 2006. Michael Hoey. Lexical priming: A new theory of words and language. International Journal of Lexicography, 19(3):327–335. DOI: https://doi.org/10.1093/ijl/ecl017 — [doi:10.1093/ijl/ecl017](https://doi.org/10.1093/ijl/ecl017) [↗](https://doi.org/10.1093/ijl/ecl017)
35. Xia, Menglin, Ekaterina Kochmar, and Ted Briscoe. 2016. Text readability assessment for second language learners. In Proceedings of the 11th Workshop on Innovative Use of NLP for Building Educational Applications, pages 12–22, San Diego, CA. DOI: https://doi.org/10.18653/v1/W16-0502, PMCID: PMC4879… [↗](https://doi.org/10.18653/v1/W16-0502) [our card](https://md.research.elamur.ai/free/en/papers/xia-2016-text-readability-assessment-second-language/)
36. Xu, Wei, Chris Callison-Burch, and Courtney Napoles. 2015. Problems in current text simplification research: New data can help. Transactions of the Association of Computational Linguistics, 3(1):283–297. DOI: https://doi.org/10.1162/tacl a 00139 [↗](https://doi.org/10.1162/tacl) [our card](https://md.research.elamur.ai/free/en/papers/xu-2015-problems-current-text-simplification-research/)
37. Yang, Zichao, Diyi Yang, Chris Dyer, Xiaodong He, Alex Smola, and Eduard Hovy. 2016. Hierarchical attention networks for document classification. In Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 1… [find](https://scholar.google.com/scholar?q=Yang%2C+Zichao%2C+Diyi+Yang%2C+Chris+Dyer%2C+Xiaodong+He%2C+Alex+Smola%2C+and+Eduard+Hovy%2E+2016%2E+Hierarchical+attention+networks+for+document+classification%2E+In+Proceedings+of+the+2016+Conference+of+the+North+Ame) [our card](https://md.research.elamur.ai/free/en/papers/yang-2016-hierarchical-attention-networks-document-classification/)
38. Zhu, Yukun, Ryan Kiros, Rich Zemel, Ruslan Salakhutdinov, Raquel Urtasun, Antonio Torralba, and Sanja Fidler. 2015. Aligning books and movies: Towards story-like visual explanations by watching movies and reading books. In Proceedings of the IEEE International Conference on Computer Vision, pages 19… [find](https://scholar.google.com/scholar?q=Zhu%2C+Yukun%2C+Ryan+Kiros%2C+Rich+Zemel%2C+Ruslan+Salakhutdinov%2C+Raquel+Urtasun%2C+Antonio+Torralba%2C+and+Sanja+Fidler%2E+2015%2E+Aligning+books+and+movies%3A+Towards+story%2Dlike+visual+explanations+by+watching+movies) [our card](https://md.research.elamur.ai/free/en/papers/zhu-2015-aligning-books-movies-towards-story/)
39. Zwitter Vitez, Ana. 2014. Ugotavljanje avtorstva besedil: primer “trenirkarjev.” In Language Technologies: Proceedings of the 17th International Multiconference Information Society - IS 2014, pages 131–134, Ljubljana. [find](https://scholar.google.com/scholar?q=Zwitter+Vitez%2C+Ana%2E+2014%2E+Ugotavljanje+avtorstva+besedil%3A+primer+%E2%80%9Ctrenirkarjev%2E%E2%80%9D+In+Language+Technologies%3A+Proceedings+of+the+17th+International+Multiconference+Information+Society+%2D+IS+2014%2C+pages+13)