A Derivational ChainBank for Modern Standard Arabic

What it is about

The paper builds a derivational resource for Modern Standard Arabic: for each root, a tree that links every derived lemma (masdar, active and passive participles, nouns of place, adjectives in -iy, and so on) to its base, through a network of abstract patterns. The network has three tables: a canonical table of root-and-pattern forms, an affixational table generated from the canonical entries plus derivational affixes, and a semantic-specification table for shifts of meaning or part of speech. The network is aligned with the lemmas of the CAMeL Morph analyzer by an allowed-pair rule on the attributes of child and parent. On 100 hand-checked root trees (25 for development, 75 for test), 71% of the test lemmas are linked (88% on development), and 92% of the detected links are correct and unambiguous. Applied to about 4,900 roots, the method gives 23,333 relations, of which about 68% are linked. The main gaps are missing primary nouns, incomplete lemma families in the analyzer, and missing non-canonical patterns.

Ideas

• I1. Use the paper's four-way score as the measure for any derivational chain built from lemmas: the share of gold lemmas linked, the share linked with one correct parent, the share with several candidate parents, and the share with none. Build the 100-tree gold set by hand from a Hebrew root list (the paper's 25/75 dev/test split is the template).
• I2. Write the Hebrew root-and-pattern forms as a canonical table (qal, niphal, piel, pual, hiphil, hophal, hitpael, and the nominal patterns of The Noun, the Adjective and the Numeral), then generate the affixed forms (for example the abstract suffix -ut and the relative -i) from that table, instead of listing them by hand.
• I3. Keep the unlinked lemmas as an explicit "unknown parent" relation rather than dropping them or forcing them onto the root. The paper suggests this for disconnected subtrees; in Mova it would show up in world as a visible gap.

For Mova

I1 is a test set and a measure for a derivational layer on top of macula dict, which has lemmas and Strong's numbers but no roots yet. I2 is a table design for The verb (binyanim) and The Noun, the Adjective and the Numeral (nominal patterns). I3 is a convention for world, to be recorded in The lexicon. None of the ideas needs a neural model.

Cite

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

@inproceedings{marzouk2025derivational,
  title = {{A Derivational ChainBank for Modern Standard Arabic}},
  author = {Marzouk, Reham and Krouna, Sondos and Habash, Nizar},
  booktitle = {Proceedings of the 1st Workshop on NLP for Languages Using Arabic Script},
  year = {2025},
  url = {https://aclanthology.org/2025.abjadnlp-1.9/}
}

References

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

1. Imad A. Al-Sughaiyer and Ibrahim A. Al-Kharashi. 2004. Arabic morphological analysis techniques: A comprehensive survey. Journal of the American Society for Information Science and Technology, 55(3):189–213. find
2. Kenneth Beesley. 1998. Arabic morphology using only https://github.com/CAMeL-Lab/ArabicChainBank finite-state operations. In Proceedings of the Workshop on Computational Approaches to Semitic Languages (CASL), pages 50–7, Montereal. ↗ our card
3. Mohamed Boudchiche, Azzeddine Mazroui, Mohamed Ould Abdallahi Ould Bebah, Abdelhak Lakhouaja, and Abderrahim Boudlal. 2017. AlKhalil Morpho Sys2: A robust Arabic morpho-syntactic analyzer. Journal of King Saud University-Computer and Information Sciences, 29(2):141–146. find
4. Abderrahim Boudlal, Abdelhak Lakhouaja, Azzeddine Mazroui, Abdelouafi Meziane, MOAO Bebah, and Mostafa Shoul. 2010. AlKhalil Morpho Sys1: A morphosyntactic analysis system for Arabic texts. In International Arab conference on information technology, pages 1–6. find
5. Ryan Cotterell, Ekaterina Vylomova, Huda Khayrallah, Christo Kirov, and David Yarowsky. 2017. Paradigm completion for derivational morphology. arXiv preprint arXiv:1708.09151. ↗
6. Hassan Gadalla. 2000. Comparative Morphology of Standard and Egyptian Arabic. LINCOM EUROPA. find
7. Nizar Habash and Bonnie Dorr. 2003. CatVar: a database of categorial variations for English. In Proceedings of Machine Translation Summit IX: System Presentations, New Orleans, USA. find our card
8. Nizar Habash, Reham Marzouk, Christian Khairallah, and Salam Khalifa. 2022. Morphotactic modeling in an open-source multi-dialectal arabic morphological analyzer and generator. In Proceedings of the 19th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology, pages 92–102. find our card
9. Nizar Habash and Owen Rambow. 2006. MAGEAD: A morphological analyzer and generator for the Arabic dialects. In Proceedings of the International Conference on Computational Linguistics and the Conference of the Association for Computational Linguistics (COLING-ACL), pages 681–688, Sydney, Australia. find our card
10. Nizar Habash, Owen Rambow, and Ryan Roth. 2012. MADA+TOKAN Manual. Technical report, Technical Report CCLS-12-01, Columbia University. find
11. 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
12. Nizar Y Habash. 2010. Introduction to Arabic natural language processing, volume 3. Morgan & Claypool Publishers. find
13. Nabil Hathout and Fiammetta Namer. 2014. Démonette, a French derivational morpho-semantic network. Linguistic Issues in Language Technology, 11. find
14. Valentin Hofmann, Hinrich Schütze, and Janet Pierrehumbert. 2020. A graph auto-encoder model of derivational morphology. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 1127–1138, Online. Association for Computational Linguistics. find
15. Clive Holes. 2004. Modern Arabic: Structures, functions, and varieties. Georgetown University Press. find
16. Nikhil Kanuparthi, Abhilash Inumella, and Dipti Misra Sharma. 2012. Hindi derivational morphological analyzer. In Proceedings of the Twelfth Meeting of the Special Interest Group on Computational Morphology and Phonology, pages 10–16. find
17. Christian Khairallah, Salam Khalifa, Reham Marzouk, Mayar Nassar, and Nizar Habash. 2024a. Camel morph MSA: A large-scale open-source morphological analyzer for Modern Standard Arabic. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 2683– 2691, Torino, Italia. ELRA and ICCL. find our card
18. Christian Khairallah, Reham Marzouk, Salam Khalifa, Mayar Nassar, and Nizar Habash. 2024b. Computational morphology and lexicography modeling of Modern Standard Arabic nominals. In Findings of the Association for Computational Linguistics: EACL 2024, pages 1071–1084, St. Julian’s, Malta. Association for Computational Linguistics. find our card
19. George Kiraz. 1994. Multi-tape Two-level Morphology: A Case study in Semitic Non-Linear Morphology. In Proceedings of the International Conference on Computational Linguistics (COLING), pages 180– 186, Kyoto, Japan. find our card
20. 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
21. Jan Šnajder. 2014. DerivBase.hr: A high-coverage derivational morphology resource for Croatian. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14), pages 3371–3377, Reykjavik, Iceland. European Language Resources Association (ELRA). find
22. Dima Taji, Jamila El Gizuli, and Nizar Habash. 2018. An Arabic dependency treebank in the travel domain. In Proceedings of the Workshop on Open-Source Arabic Corpora and Processing Tools (OS-ACT), Miyazaki, Japan. find our card
23. Daniil Vodolazsky. 2020. Derivbase. ru: A derivational morphology resource for Russian. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 3937–3943. find
24. Wajdi Zaghouani, Abdelati Hawwari, Mona Diab, Tim O’Gorman, and Ahmed Badran. 2016. AMPN: a semantic resource for Arabic morphological patterns. International Journal of Speech Technology, 19:281– 288. find
25. Britta Zeller, Jan Šnajder, and Sebastian Padó. 2013. DErivBase: Inducing and evaluating a derivational morphology resource for German. In Proceedings of the Association for Computational Linguistics, pages 1201–1211. find

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/aclbulk-2025-marzouk-derivational-chainbank-modern-standard-arabic/