Elamur Research⌕
☰
home / papers / 2022 / Arabic Word-level Readability Visualization for Assisted Text Simplification

Arabic Word-level Readability Visualization for Assisted Text Simplification

Summary

Most readability tools score whole documents or sentences, so a human simplifier still has to find the specific words that need rewriting. The authors work within the SAMER project, which simplifies Arabic novels for school-age readers, and they built a Google Docs add-on that colours every word by difficulty. Modern Standard Arabic is morphologically rich and usually written without diacritics, so the tool first tokenizes the text. It then runs a JavaScript port of the Buckwalter morphological analysis algorithm, with light disambiguation, to choose the most likely lemma and POS for each token. That lemma is looked up in the five-level readability lexicon of Al Khalil et al. (2020), and the word is highlighted. The add-on also reports how tokens and types are spread across levels. When a user selects a word, a side panel shows its other possible analyses and Arabic WordNet-based substitutes, each with its own level. Users can correct levels, and these corrections are kept as inline markup. The code is public, but the paper reports no formal evaluation. The tool serves as annotation infrastructure for a parallel corpus of original and simplified Arabic texts.

Key points

  • The readability scale has five levels tied to school grades: Level I up to Level V for grades 9 and above. The lexicon originally held 26,578 lemmas and was later extended to over 40,000.
  • The processing pipeline has four steps: preprocessing and tokenization (non-words are dropped), lemma and POS selection by the analyzer, lexicon lookup, and highlighting with summary statistics. Proper nouns get their own category.
  • Four markup modes control how visible the explicit level annotations are: Show, Minimize (1pt font), Hide (keeps only annotations that disagree with the analyzer), and Delete. "Assign" and "Assign All" let users override the level of one occurrence or of every occurrence.
  • SAMER plans two simplified targets: Grades 4–5 (Level III) and Grades 6–8 (Level IV).
  • Porting the tool to another language would need four components:
    • a lemma-to-level lexicon;
    • a morphological database of prefixes, stems, suffixes and their compatibilities;
    • a statistical lemma disambiguator;
    • WordNet-style lexical relations.

Interesting ideas

  • I1. Anchor difficulty at the lemma, not the inflected form, so that a single entry covers every inflected and cliticized variant of a word. — For Mova (tokens): crate en could attach a graded-difficulty attribute to each lemma, so that morphology output directly supports per-word readability checks.
  • I2. Store human corrections as explicit markup that survives later versions of the analyzer and lexicon, and offer a view that shows reviewers only the spots where markup and fresh automatic output disagree. — For Mova (learn): silver-data corrections could be stored as persistent overrides and re-diffed against each new parser or teacher version, with only disagreements shown for review.
  • I3. Give every substitution candidate its own difficulty level, so rewriting becomes a constrained choice rather than a blind synonym swap. — For Mova (back): during generation from the meaning graph, lexical choice could be filtered by a target level, giving simplified retellings of fables and tales.
  • I4. Let the user see all competing morphological analyses with their consequences, rather than hiding everything except the analyzer's pick. — For Mova (tokens): the tagger and lemmatizer could expose the rejected analyses and their downstream effects, which supports the explainability requirement at every step.
  • I5. Put names in a separate class so they do not inflate a text's apparent difficulty. — For Mova (answer): readability or level estimates for school-course reading tasks could exclude proper nouns, so that character names in tales are not mistaken for hard vocabulary.

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 · Natural language processing

Cited by

26 papers of our library cite it (of the 140884 whose bibliographies we read); 4 of them have a page here, 22 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2022.emnlp-demos.24

@inproceedings{hazim2022arabic,
  title = {{Arabic Word-level Readability Visualization for Assisted Text Simplification}},
  author = {Hazim, Reem and Saddiki, Hind and Alhafni, Bashar and Khalil, Muhamed Al and Habash, Nizar},
  booktitle = {Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations},
  year = {2022},
  doi = {10.18653/v1/2022.emnlp-demos.24},
  url = {https://doi.org/10.18653/v1/2022.emnlp-demos.24}
}

References

36 references, 9 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Ali Al-Jarim. 1945. Fāris Banı̄ H . amdān (The Knight of Bani Hamdan). Hindawi Foundation. find
  2. Hend S Al-Khalifa and Amani A Al-Ajlan. 2010. Automatic readability measurements of the Arabic text: An exploratory study. Arabian Journal for Science and Engineering, 35(2 C):103–124. find
  3. Muhamed Al Khalil, Nizar Habash, and Zhengyang Jiang. 2020. A large-scale leveled readability lexicon for Standard Arabic. In Proceedings of the 12th Language Resources and Evaluation Conference, pages 3053–3062, Marseille, France. European Language Resources Association. find our card
  4. Muhamed Al Khalil, Nizar Habash, and Hind Saddiki. 2017. Simplification of Arabic masterpieces for extensive reading: A project overview. Procedia Computer Science, 117:192–198. find
  5. Muhamed Al Khalil, Hind Saddiki, Nizar Habash, and Latifa Alfalasi. 2018. A leveled reading corpus of Modern Standard Arabic. In Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018), Miyazaki, Japan. European Language Resources Association (ELRA). find
  6. Abdel Karim Al Tamimi, Manar Jaradat, Nuha Al-Jarrah, and Sahar Ghanem. 2014. AARI: automatic Arabic readability index. International Arab Journal of Information Technology, 11(4):370–378. find
  7. William Black, Sabri Elkateb, Horacio Rodriguez, Musa Alkhalifa, Piek Vossen, Adam Pease, and Christiane Fellbaum. 2006. Introducing the Arabic wordnet project. In Proceedings of the Global WordNet Conference (GWC), pages 295–300. find
  8. Mahmoud El-Haj and Paul Rayson. 2016. OSMAN — a novel Arabic readability metric. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16), pages 250–255, Portorož, Slovenia. European Language Resources Association (ELRA). find
  9. Christiane Fellbaum. 2010. Wordnet. In Theory and Applications of Ontology: Computer Applications, pages 231–243. Springer. find
  10. Lijun Feng, Martin Jansche, Matt Huenerfauth, and Noémie Elhadad. 2010. A comparison of features for automatic readability assessment. In Coling 2010: Posters, pages 276–284, Beijing, China. Coling 2010 Organizing Committee. find our card
  11. Charles F Ferguson. 1959. Diglossia. Word, 15(2):325– 340. find
  12. Jonathan Forsyth. 2014. Automatic readability prediction for modern standard Arabic. In Proceedings of the Workshop on Open-Source Arabic Corpora and Processing Tools (OSACT). find
  13. David Graff, Mohamed Maamouri, Basma Bouziri, Sondos Krouna, Seth Kulick, and Tim Buckwalter. 2009. Standard Arabic Morphological Analyzer (SAMA) Version 3.1. Linguistic Data Consortium LDC2009E73. find
  14. Nizar Habash, Abdelhadi Soudi, and Tim Buckwalter. 2007. On Arabic Transliteration. In A. van den Bosch and A. Soudi, editors, Arabic Computational Morphology: Knowledge-based and Empirical Methods, pages 15–22. Springer, Netherlands. find
  15. Nizar Y Habash. 2010. Introduction to Arabic natural language processing, volume 3. Morgan & Claypool Publishers. find
  16. Tim Buckwalter. 2002. Buckwalter Arabic morphological analyzer version 1.0. Linguistic Data Consortium (LDC) catalog number LDC2002L49, ISBN 1-58563-257-0. find
  17. Clive Holes. 2004. Modern Arabic: Structures, Functions, and Varieties. Georgetown Classics in Arabic Language and Linguistics. Georgetown University Press. find
  18. Kevin S Carroll, Bashar Al Kahwaji, and David Litz. 2017. Triglossia and promoting Arabic literacy in the United Arab Emirates. Language, Culture and Curriculum, 30(3):317–332. find
  19. Zhengyang Jiang, Nizar Habash, and Muhamed Al Khalil. 2020. An online readability leveled Arabic thesaurus. In Proceedings of the 28th International Conference on Computational Linguistics: System Demonstrations, pages 59–63, Barcelona, Spain (Online). International Committee on Computational Linguistics (ICCL). find
  20. Kevyn Collins-Thompson and James P. Callan. 2004. A language modeling approach to predicting reading difficulty. In Proceedings of the Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics: HLT-NAACL 2004, pages 193–200, Boston, Massachusetts, USA. Association for Computational Linguistics. find
  21. Kareem Darwish and Hamdy Mubarak. 2016. Farasa: A new fast and accurate Arabic word segmenter. In Proceedings of the Language Resources and Evaluation Conference (LREC), Portorož, Slovenia. find
  22. Tovly Deutsch, Masoud Jasbi, and Stuart Shieber. 2020. Linguistic features for readability assessment. In Proceedings of the Fifteenth Workshop on Innovative Use of NLP for Building Educational Applications, pages 1–17, Seattle, WA, USA → Online. Association for Computational Linguistics. find
  23. Salam Khalifa, Houda Bouamor, and Nizar Habash. 2016. DALILA: The dialectal Arabic linguistic learning assistant. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16), pages 1098–1102, Portorož, Slovenia. European Language Resources Association (ELRA). find
  24. Muhamed Al Khalil, Hind Saddiki, Nizar Habash, and Latifa Alfalasi. 2018. A Leveled Reading Corpus of Modern Standard Arabic. In Proceedings of the Language Resources and Evaluation Conference (LREC), Miyazaki, Japan. find
  25. Bruce W. Lee, Yoo Sung Jang, and Jason Lee. 2021. Pushing on text readability assessment: A transformer meets handcrafted linguistic features. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 10669– 10686, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics. find
  26. Farah Nadeem 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, Louisiana. Association for Computational Linguistics. find
  27. Ossama Obeid, Go Inoue, and Nizar Habash. 2022. Camelira: An Arabic Multi-Dialect Morphological Disambiguator. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP 2022) Demo Track, Abu Dhabi, United Arab Emirates. find our card
  28. Ossama Obeid, Nasser Zalmout, Salam Khalifa, Dima Taji, Mai Oudah, Bashar Alhafni, Go Inoue, Fadhl Eryani, Alexander Erdmann, and Nizar Habash. 2020. CAMeL tools: An open source python toolkit for Arabic natural language processing. In Proceedings of The 12th Language Resources and Evaluation Conference, pages 7022–7032, Marseille, France. European Language Resources Association. insights from second language acquisition. In Proceedings of the Seventh Workshop on Building Educational Applications Using NLP, pages 163–173, Montréal, Canada. Association for Computational Linguistics. find our card
  29. Rodrigo Wilkens, David Alfter, Xiaoou Wang, Alice Pintard, Anaïs Tack, Kevin P. Yancey, and Thomas François. 2022. Fabra: French aggregator-based readability assessment toolkit. In Proceedings of the Language Resources and Evaluation Conference, pages 1217–1233, Marseille, France. European Language Resources Association. find
  30. Menglin Xia, 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. Association for Computational Linguistics. find our card
  31. Arfath Pasha, Mohamed Al-Badrashiny, Mona Diab, Ahmed El Kholy, Ramy Eskander, Nizar Habash, Manoj Pooleery, Owen Rambow, and Ryan Roth. 2014. Madamira: A fast, comprehensive tool for morphological analysis and disambiguation of Arabic. In Proceedings of the Language Resources and Evaluation Conference (LREC), pages 1094–1101, Reykjavik, Iceland. find our card
  32. 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, pages 186–195, Honolulu, Hawaii. Association for Computational Linguistics. find our card
  33. Hind Saddiki, Nizar Habash, Violetta Cavalli-Sforza, and Muhamed Al Khalil. 2018. Feature optimization for predicting readability of Arabic L1 and L2. In Proceedings of the 5th Workshop on Natural Language Processing Techniques for Educational Applications, pages 20–29, Melbourne, Australia. Association for Computational Linguistics. find
  34. Dima Taji, Salam Khalifa, Ossama Obeid, Fadhl Eryani, and Nizar Habash. 2018. An Arabic Morphological Analyzer and Generator with Copious Features. In Proceedings of the Fifteenth Workshop on Computational Research in Phonetics, Phonology, and Morphology (SIGMORPHON), pages 140–150. find our card
  35. Sowmya Vajjala and Ivana Lučić. 2018. OneStopEnglish corpus: A new corpus for automatic readability assessment and text simplification. In Proceedings of the Thirteenth Workshop on Innovative Use of NLP for Building Educational Applications, pages 297–304, New Orleans, Louisiana. Association for Computational Linguistics. find our card
  36. Sowmya Vajjala and Detmar Meurers. 2012. On improving the accuracy of readability classification using find

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/hazim-2022-arabic-word-level-readability-visualization/