---
title: "READ–IT: Assessing Readability of — Dell'Orletta 2011"
description: "The paper presents READ–IT, which the authors describe as the first advanced readability assessment tool for Italian."
authors: ["Felice Dell'Orletta", "Simonetta Montemagni", "Giulia Venturi"]
year: 2011
venue: "Proceedings of the Second Workshop on Speech and Language Processing for Assistive Technologies"
source: "https://aclanthology.org/W11-2308/"
licence: "CC BY-NC-SA 3.0 (ACL Anthology, before 2016)"
licence_url: "https://creativecommons.org/licenses/by-nc-sa/3.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/papers/orletta-2011-read-it-assessing-readability-italian/"
---
[Elamur Research](https://md.research.elamur.ai/) · [this page in HTML](https://research.elamur.ai/free/papers/orletta-2011-read-it-assessing-readability-italian/)

[home](https://md.research.elamur.ai/) / [papers](https://md.research.elamur.ai/free/papers/) / [2011](https://md.research.elamur.ai/free/papers/2011/) / READ–IT: Assessing Readability of Italian Texts with a View to Text Simplification

# READ–IT: Assessing Readability of Italian Texts with a View to Text Simplification

**Authors:** [Felice Dell'Orletta](https://md.research.elamur.ai/free/authors/felice-dell-orletta/), [Simonetta Montemagni](https://md.research.elamur.ai/free/authors/simonetta-montemagni/), [Giulia Venturi](https://md.research.elamur.ai/free/authors/giulia-venturi/) · **Year:** 2011 · **Venue:** Proceedings of the Second Workshop on Speech and Language Processing for Assistive Technologies · **Licence:** [CC BY-NC-SA 3.0 (ACL Anthology, before 2016)](https://creativecommons.org/licenses/by-nc-sa/3.0/)

**Links:** [Publisher's page](https://aclanthology.org/W11-2308/) · [PDF](https://aclanthology.org/W11-2308.pdf) · [OpenAlex](https://openalex.org/W1655573795)

**Citations:** 132 citations (openalex-snapshot · 2026-10-14) · [76](#cited-by) in our library, of the 140673 papers whose bibliographies we read

## Summary
The paper presents READ–IT, which the authors describe as the first advanced readability assessment tool for Italian. It targets text simplification for readers with low literacy or mild cognitive impairment. Readability is treated as a binary task that separates easy-to-read from difficult-to-read material. The easy class is represented by the 2Par corpus and the difficult class by the Rep newspaper corpus.

Four feature sets are compared, each building on the previous one: raw text (Base), lexical, morpho-syntactic (MorphoS) and syntactic (Syntax). The tool classifies whole documents and also single sentences, which earlier work had largely ignored. Sentence-level gold labels do not exist, because a complex text can still contain easy sentences. To get around this, the authors measure how far classified sentences lie from the easy reference corpus.

Document classification reaches high accuracy, with MorphoS performing best. At the sentence level, syntactic features help much more. Sentence-level assessment matters because it lets readability scoring point to the specific sentences a simplification system should rewrite.

## Key points
- Italian previously relied on surface formulas such as Flesch-Vacca and the GulpEase index. READ–IT adds lexical, morpho-syntactic and syntactic information to these raw-text signals.
- Four models are compared: Base, Lexical, MorphoS and Syntax.
  - For documents, MorphoS beats the Lexical model by about 2.6%.
  - For sentences, the Syntax Model beats it by about 17%.
- On the Rep test set, the Syntax Model wrongly assigned 140 sentences to 2Par. Their distance to 2Par was the lowest of the groups:
  - wrongly classified sentences: 37.843
  - full test set: 45.361
  - correctly classified sentences: 52.072
- On the unlabeled Rep 2.5 corpus, the share of sentences labelled difficult grows with richer features:
  - Base: 0.234
  - Lexical: 0.387
  - MorphoS: 0.705
  - Syntax: 0.755
- Sentences labelled easy by the Syntax Model are closest to 2Par (51.408). Those it labels difficult are farthest (66.526).

## Interesting ideas
- **Distance to a reference corpus as a proxy for gold labels.** When no gold labels exist, comparing predicted classes against a trusted reference corpus still lets you rank competing models. This fits any low-resource task where only one class has clean examples.
- **Length-controlled evaluation.** The authors compare sentences of equal length (8–30 tokens) with same-length sentences from 2Par. In that setting the raw-feature Base model turned out to be no better than the unfiltered corpus. Controlling for an obvious confounder like this can expose models that only learn shallow cues.
- **Errors may not be errors.** The authors recognize that "misclassified" difficult-class items may actually be easy sentences sitting inside hard texts. Checking whether such errors look like the other class is a useful sanity check whenever labels are inherited from the document level.
- **Features chosen with the downstream task in mind.** The authors prefer features that NLP tools can extract reliably and include features oriented toward simplification. This makes the assessment output directly usable by a later rewriting step, which suits other pipelines that chain diagnosis and generation.
- **Measuring what each feature layer adds.** Adding feature groups one at a time shows that the levels matter differently by granularity: morpho-syntax helps most for documents and syntax for sentences. This cheap ablation design is easy to reuse in other classification work.

*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: [Machine translation](https://md.research.elamur.ai/free/shelves/machine-translation/) · [Natural language processing](https://md.research.elamur.ai/free/shelves/nlp/)

## Cited by

Cited by

76 papers of our library cite it (of the 140673 whose bibliographies we read); 3 of them have a page here, 73 not yet.

- [Evaluating LLM Style Transfer Through Readability-Based Age Assessments](https://md.research.elamur.ai/free/papers/maro-2026-evaluating-llm-style-transfer-through/)
- [Controllable Sentence Simplification in Italian: Fine-Tuning Large Language Models on Automatically Generated Resources](https://md.research.elamur.ai/free/papers/papucci-2026-controllable-sentence-simplification-italian-fine/)
- [OneStopEnglish corpus: A new corpus for automatic readability assessment and text simplification](https://md.research.elamur.ai/free/papers/vajjala-2018-onestopenglish-corpus-new-corpus-automatic/)

## Cite

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

```bibtex
@inproceedings{dellorletta2011read,
  title = {{READ–IT: Assessing Readability of Italian Texts with a View to Text Simplification}},
  author = {Dell'Orletta, Felice and Montemagni, Simonetta and Venturi, Giulia},
  booktitle = {Proceedings of the Second Workshop on Speech and Language Processing for Assistive Technologies},
  year = {2011},
  url = {https://aclanthology.org/W11-2308/}
}
```

- [← previous Putting it Simply: a Context-Aware Approach to Lexical Simplification](https://md.research.elamur.ai/free/papers/biran-2011-putting-it-simply-context-aware/)
- [next → RelaxCor Participation in CoNLL Shared Task on Coreference Resolution](https://md.research.elamur.ai/free/papers/sapena-2011-relaxcor-participation-conll-shared-task/)
- [↑ back to papers of 2011](https://md.research.elamur.ai/free/papers/2011/)

## References

35 references, 4 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Sandra Aluisio, Lucia Specia, Caroline Gasperin and Carolina Scarton. 2010. Readability assessment for text simplification. In Proceedings of the NAACL HLT 2010 Fifth Workshop on Innovative Use of NLP for Building Educational Applications, pp. 1–9. [find](https://scholar.google.com/scholar?q=Sandra+Aluisio%2C+Lucia+Specia%2C+Caroline+Gasperin+and+Carolina+Scarton%2E+2010%2E+Readability+assessment+for+text+simplification%2E+In+Proceedings+of+the+NAACL+HLT+2010+Fifth+Workshop+on+Innovative+Use+of+NLP) [our card](https://md.research.elamur.ai/free/papers/aluisio-2010-readability-assessment-text-simplification/)
2. Giuseppe Attardi. 2006. Experiments with a multilanguage non-projective dependency parser. In Proceedings of the Tenth Conference on Computational Natural Language Learning (CoNLL-X ’06), New York City, New York, pp. 166–170. [find](https://scholar.google.com/scholar?q=Giuseppe+Attardi%2E+2006%2E+Experiments+with+a+multilanguage+non%2Dprojective+dependency+parser%2E+In+Proceedings+of+the+Tenth+Conference+on+Computational+Natural+Language+Learning+%28CoNLL%2DX+%E2%80%9906%29%2C+New+York+Cit) [our card](https://md.research.elamur.ai/free/papers/attardi-2006-experiments-multilanguage-non-projective-dependency/)
3. Regina Barzilay and Mirella Lapata. 2008. Modeling local coherence: An entity-based approach. In Computational Linguistics, 34(1), pp. 1–34. [↗](https://doi.org/10.1162/coli.2008.34.1.1) [our card](https://md.research.elamur.ai/free/papers/barzilay-2008-modeling-local-coherence-entity-based/)
4. Douglas Biber and Susan Conrad. 2009. Register, genre, and style. Cambridge, Cambridge University Press. [↗](https://doi.org/10.1017/cbo9780511814358)
5. Tim vor der Brück, Sven Hartrumpf, Hermann Helbig. 2008. A Readability Checker with Supervised Learning using Deep Syntactic and Semantic Indicators. In Proceedings of the 11th International Multiconference: Information Society - IS 2008 - Language Technologies, Ljubljana, Slovenia, pp. 92–97. [find](https://scholar.google.com/scholar?q=Tim+vor+der+Bru%CC%88ck%2C+Sven+Hartrumpf%2C+Hermann+Helbig%2E+2008%2E+A+Readability+Checker+with+Supervised+Learning+using+Deep+Syntactic+and+Semantic+Indicators%2E+In+Proceedings+of+the+11th+International+Multicon)
6. Jeanne S. Chall and Edgar Dale. 1995. Readability Revisited: The New Dale–Chall Readability Formula. Brookline Books, Cambridge, MA. [find](https://scholar.google.com/scholar?q=Jeanne+S%2E+Chall+and+Edgar+Dale%2E+1995%2E+Readability+Revisited%3A+The+New+Dale%E2%80%93Chall+Readability+Formula%2E+Brookline+Books%2C+Cambridge%2C+MA%2E)
7. Chih-Chung Chang and Chih-Jen Lin. 2001. LIB-SVM: a library for support vector machines. Software available at [http://www.csie.ntu.edu](http://www.csie.ntu.edu). tw/˜cjlin/libsvm Kevyn Collins-Thompson and Jamie Callan. 2004. A language modeling approach to predicting reading difficulty. In Proceedings of the HLT / NAACL, pp. 193– 200. [↗](http://www.csie.ntu.edu)
8. Felice Dell’Orletta. 2009. Ensemble system for Part-of-Speech tagging. In Proceedings of Evalita’09, Evaluation of NLP and Speech Tools for Italian, Reggio Emilia, December. [find](https://scholar.google.com/scholar?q=Felice+Dell%E2%80%99Orletta%2E+2009%2E+Ensemble+system+for+Part%2Dof%2DSpeech+tagging%2E+In+Proceedings+of+Evalita%E2%80%9909%2C+Evaluation+of+NLP+and+Speech+Tools+for+Italian%2C+Reggio+Emilia%2C+December%2E)
9. Tullio De Mauro. 2000. Il dizionario della lingua italiana. Torino, Paravia. [find](https://scholar.google.com/scholar?q=Tullio+De+Mauro%2E+2000%2E+Il+dizionario+della+lingua+italiana%2E+Torino%2C+Paravia%2E)
10. Lijun Feng, Martin Jansche, Matt Huenerfauth and Noémie Elhadad. 2010. A comparison of features for automatic readability assessment. In Proceedings of the 23rd International Conference on Computational Linguistics (COLING 2010), pp. 276–284. [find](https://scholar.google.com/scholar?q=Lijun+Feng%2C+Martin+Jansche%2C+Matt+Huenerfauth+and+Noe%CC%81mie+Elhadad%2E+2010%2E+A+comparison+of+features+for+automatic+readability+assessment%2E+In+Proceedings+of+the+23rd+International+Conference+on+Computatio)
11. Lijun Feng, Noémie Elhadad and Matt Huenerfauth. 2009. Cognitively motivated features for readability assessment. In Proceedings of the 12th Conference of the European Chapter of the Association for Computational Linguistics (EACL ’09), pp. 229–237. [find](https://scholar.google.com/scholar?q=Lijun+Feng%2C+Noe%CC%81mie+Elhadad+and+Matt+Huenerfauth%2E+2009%2E+Cognitively+motivated+features+for+readability+assessment%2E+In+Proceedings+of+the+12th+Conference+of+the+European+Chapter+of+the+Association+for+)
12. V. Franchina and Roberto Vacca. 1986. Adaptation of Flesh readability index on a bilingual text written by the same author both in Italian and English languages. In Linguaggi (3), pp. 47–49. [find](https://scholar.google.com/scholar?q=V%2E+Franchina+and+Roberto+Vacca%2E+1986%2E+Adaptation+of+Flesh+readability+index+on+a+bilingual+text+written+by+the+same+author+both+in+Italian+and+English+languages%2E+In+Linguaggi+%283%29%2C+pp%2E+47%E2%80%9349%2E)
13. Lyn Frazier. 1985. Syntactic complexity. In D.R. Dowty, L. Karttunen and A.M. Zwicky (eds.), Natural Language Parsing, Cambridge University Press, Cambridge, UK. [find](https://scholar.google.com/scholar?q=Lyn+Frazier%2E+1985%2E+Syntactic+complexity%2E+In+D%2ER%2E+Dowty%2C+L%2E+Karttunen+and+A%2EM%2E+Zwicky+%28eds%2E%29%2C+Natural+Language+Parsing%2C+Cambridge+University+Press%2C+Cambridge%2C+UK%2E)
14. Edward Gibson. 1998. Linguistic complexity: Locality of syntactic dependencies. In Cognition, 68(1), pp. 1-76. [↗](https://doi.org/10.1016/s0010-0277(98)00034-1)
15. Michael J. Heilman, Kevyn Collins and Jamie Callan. 2007. Combining Lexical and Grammatical Features to Improve Readability Measures for First and Second Language Texts. In Proceedings of the Human Language Technology Conference, pp. 460–467. [find](https://scholar.google.com/scholar?q=Michael+J%2E+Heilman%2C+Kevyn+Collins+and+Jamie+Callan%2E+2007%2E+Combining+Lexical+and+Grammatical+Features+to+Improve+Readability+Measures+for+First+and+Second+Language+Texts%2E+In+Proceedings+of+the+Human+La)
16. Michael J. Heilman, Kevyn Collins and Maxine Eskenazi. 2008. An analysis of statistical models and features for reading difficulty prediction. In Proceedings of the Third Workshop on Innovative Use of NLP for Building Educational Applications (EANL ’08), pp. 71–79. [find](https://scholar.google.com/scholar?q=Michael+J%2E+Heilman%2C+Kevyn+Collins+and+Maxine+Eskenazi%2E+2008%2E+An+analysis+of+statistical+models+and+features+for+reading+difficulty+prediction%2E+In+Proceedings+of+the+Third+Workshop+on+Innovative+Use+of)
17. Rohit J. Kate, Xiaoqiang Luo, Siddharth Patwardhan, Martin Franz, Radu Florian, Raymond J. Mooney, Salim Roukos, Chris Welty. 2010. Learning to Predict Readability using Diverse Linguistic Features. In Proceedings of the 23rd International Conference on Computational Linguistics (COLING 2010), pp. 546– 554. [find](https://scholar.google.com/scholar?q=Rohit+J%2E+Kate%2C+Xiaoqiang+Luo%2C+Siddharth+Patwardhan%2C+Martin+Franz%2C+Radu+Florian%2C+Raymond+J%2E+Mooney%2C+Salim+Roukos%2C+Chris+Welty%2E+2010%2E+Learning+to+Predict+Readability+using+Diverse+Linguistic+Features%2E+I)
18. J. Peter Kincaid, Lieutenant Robert P. Fishburne, Richard L. Rogers and Brad S. Chissom. 1975. Derivation of new readability formulas for Navy enlisted personnel. Research Branch Report, Millington, TN: Chief of Naval Training, pp. 8–75. [find](https://scholar.google.com/scholar?q=J%2E+Peter+Kincaid%2C+Lieutenant+Robert+P%2E+Fishburne%2C+Richard+L%2E+Rogers+and+Brad+S%2E+Chissom%2E+1975%2E+Derivation+of+new+readability+formulas+for+Navy+enlisted+personnel%2E+Research+Branch+Report%2C+Millington%2C+T)
19. George Kingsley Zipf. 1988. The Psychobiology of Language. Houghton–Miflin, Boston. [find](https://scholar.google.com/scholar?q=George+Kingsley+Zipf%2E+1988%2E+The+Psychobiology+of+Language%2E+Houghton%E2%80%93Miflin%2C+Boston%2E)
20. Dekan Lin. 1996. On the structural complexity of natural language sentences. In Proceedings of COLING 1996, pp. 729–733. [find](https://scholar.google.com/scholar?q=Dekan+Lin%2E+1996%2E+On+the+structural+complexity+of+natural+language+sentences%2E+In+Proceedings+of+COLING+1996%2C+pp%2E+729%E2%80%93733%2E)
21. Pietro Lucisano and Maria Emanuela Piemontese. 1988. Gulpease. Una formula per la predizione della difficoltà dei testi in lingua italiana. In Scuola e Città (3), pp. 57–68. [find](https://scholar.google.com/scholar?q=Pietro+Lucisano+and+Maria+Emanuela+Piemontese%2E+1988%2E+Gulpease%2E+Una+formula+per+la+predizione+della+difficolta%CC%80+dei+testi+in+lingua+italiana%2E+In+Scuola+e+Citta%CC%80+%283%29%2C+pp%2E+57%E2%80%9368%2E)
22. Ryan McDonald and Joakim Nivre. 2007. Characterizing the Errors of Data-Driven Dependency Parsing Models. In Proceedings of EMNLP-CoNLL, 2007, pp. 122-131. [find](https://scholar.google.com/scholar?q=Ryan+McDonald+and+Joakim+Nivre%2E+2007%2E+Characterizing+the+Errors+of+Data%2DDriven+Dependency+Parsing+Models%2E+In+Proceedings+of+EMNLP%2DCoNLL%2C+2007%2C+pp%2E+122%2D131%2E) [our card](https://md.research.elamur.ai/free/papers/missing4-2007-mcdonald-characterizing-errors-data-driven-dependency/)
23. Jim Miller and Regina Weinert. 1998. Spontaneous spoken language. Syntax and discourse. Oxford, Clarendon Press. [↗](https://doi.org/10.1093/oso/9780198236566.001.0001)
24. Ani Nenkova, Jieun Chae, Annie Louis, and Emily Pitler. 2010. Structural Features for Predicting the Linguistic Quality of Text Applications to Machine Translation, Automatic Summarization and Human–Authored Text. In E. Krahmer, M. Theune (eds.), Empirical Methods in NLG, LNAI 5790, Springer-Verlag Berlin Heidelberg, pp. 222–241. [find](https://scholar.google.com/scholar?q=Ani+Nenkova%2C+Jieun+Chae%2C+Annie+Louis%2C+and+Emily+Pitler%2E+2010%2E+Structural+Features+for+Predicting+the+Linguistic+Quality+of+Text+Applications+to+Machine+Translation%2C+Automatic+Summarization+and+Human%E2%80%93A)
25. Sarah E. Petersen and Mari Ostendorf. 2006. A machine learning approach to reading level assessment. University of Washington CSE Technical Report. [find](https://scholar.google.com/scholar?q=Sarah+E%2E+Petersen+and+Mari+Ostendorf%2E+2006%2E+A+machine+learning+approach+to+reading+level+assessment%2E+University+of+Washington+CSE+Technical+Report%2E)
26. Sarah E. Petersen and Mari Ostendorf. 2009. A machine learning approach to reading level assessment. In Computer Speech and Language (23), pp. 89–106. [↗](https://doi.org/10.1016/j.csl.2008.04.003)
27. Maria Emanuela Piemontese. 1996. Capire e farsi capire. Teorie e tecniche della scrittura controllata Napoli, Tecnodid. [find](https://scholar.google.com/scholar?q=Maria+Emanuela+Piemontese%2E+1996%2E+Capire+e+farsi+capire%2E+Teorie+e+tecniche+della+scrittura+controllata+Napoli%2C+Tecnodid%2E)
28. Emily Pitler and Ani Nenkova. 2008. Revisiting readability: A unified framework for predicting text quality. In Proceedings of the 2008 Conference on Empirical Methods in Natural Language Processing, pp. 186–195. [find](https://scholar.google.com/scholar?q=Emily+Pitler+and+Ani+Nenkova%2E+2008%2E+Revisiting+readability%3A+A+unified+framework+for+predicting+text+quality%2E+In+Proceedings+of+the+2008+Conference+on+Empirical+Methods+in+Natural+Language+Processing%2C+)
29. Kristine Retherford. 2003. Normal development: a database of communication and related behaviors. Eau Claire, WI: Thinking Publications. [find](https://scholar.google.com/scholar?q=Kristine+Retherford%2E+2003%2E+Normal+development%3A+a+database+of+communication+and+related+behaviors%2E+Eau+Claire%2C+WI%3A+Thinking+Publications%2E)
30. Brian Roark, Margaret Mitchell and Kristy Hollingshead. 2007. Syntactic complexity measures for detecting mild cognitive impairment. In Proceedings of the Workshop on BioNLP 2007: Biological, Translational, and Clinical Language Processing, pp. 1–8. [find](https://scholar.google.com/scholar?q=Brian+Roark%2C+Margaret+Mitchell+and+Kristy+Hollingshead%2E+2007%2E+Syntactic+complexity+measures+for+detecting+mild+cognitive+impairment%2E+In+Proceedings+of+the+Workshop+on+BioNLP+2007%3A+Biological%2C+Translat)
31. Sarah E. Schwarm and Mari Ostendorf. 2005. Reading level assessment using support vector machines and statistical language models. In Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics (ACL 05), pp. 523–530. [find](https://scholar.google.com/scholar?q=Sarah+E%2E+Schwarm+and+Mari+Ostendorf%2E+2005%2E+Reading+level+assessment+using+support+vector+machines+and+statistical+language+models%2E+In+Proceedings+of+the+43rd+Annual+Meeting+on+Association+for+Computat)
32. Luo Si and Jamie Callan. 2001. A statistical model for scientific readability. In Proceedings of the tenth international conference on Information and knowledge management, pp. 574–576. [find](https://scholar.google.com/scholar?q=Luo+Si+and+Jamie+Callan%2E+2001%2E+A+statistical+model+for+scientific+readability%2E+In+Proceedings+of+the+tenth+international+conference+on+Information+and+knowledge+management%2C+pp%2E+574%E2%80%93576%2E)
33. Adam Skory and Maxine Eskenazi. 2010. Predicting cloze task quality for vocabulary training. In Proceedings of the NAACL HLT 2010 Fifth Workshop on Innovative Use of NLP for Building Educational Applications, pp. 49–56. [find](https://scholar.google.com/scholar?q=Adam+Skory+and+Maxine+Eskenazi%2E+2010%2E+Predicting+cloze+task+quality+for+vocabulary+training%2E+In+Proceedings+of+the+NAACL+HLT+2010+Fifth+Workshop+on+Innovative+Use+of+NLP+for+Building+Educational+Appli)
34. Victor H.A. Yngve. 1960. A model and an hypothesis for language structure. In Proceedings of the American Philosophical Society, pp. 444-466. [find](https://scholar.google.com/scholar?q=Victor+H%2EA%2E+Yngve%2E+1960%2E+A+model+and+an+hypothesis+for+language+structure%2E+In+Proceedings+of+the+American+Philosophical+Society%2C+pp%2E+444%2D466%2E)
35. Heather Harris Wright, Stacy W. Silverman and Marilyn Newhoff. 2003. Measures of lexical diversity in aphasia. In Aphasiology, 17(5), pp. 443-452. [↗](https://doi.org/10.1080/02687030344000166)