--- title: "Al –-Khalil : The Arabic Linguistic Ontology Project — Aliane 2010" description: "The authors describe early work on Al-Khalil, an OWL ontology of Arabic linguistics grounded in Arabic Traditional… 7 references, cited by 2 papers here." authors: ["Hassina Aliane", "Zaia Alimazighi", "Ahmed Cherif Mazari"] year: 2010 venue: "Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10)" source: "https://aclanthology.org/L10-1437/" licence: "CC BY-NC 4.0 (ELRA, LREC proceedings)" licence_url: "https://creativecommons.org/licenses/by-nc/4.0/" summary_licence: "Elamur Cosmic License" canonical: "https://research.elamur.ai/free/en/papers/aliane-2010-al-khalil-arabic-linguistic-ontology/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/aliane-2010-al-khalil-arabic-linguistic-ontology/) [home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2010](https://md.research.elamur.ai/free/en/papers/2010/page/2/) / Al –-Khalil : The Arabic Linguistic Ontology Project # Al –-Khalil : The Arabic Linguistic Ontology Project **Authors:** [Hassina Aliane](https://md.research.elamur.ai/free/en/authors/hassina-aliane/), Zaia Alimazighi and Ahmed Cherif Mazari · **Year:** 2010 · **Venue:** Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10) · **Licence:** [CC BY-NC 4.0 (ELRA, LREC proceedings)](https://creativecommons.org/licenses/by-nc/4.0/) **Links:** [Publisher's page](https://aclanthology.org/L10-1437/) · [PDF](https://aclanthology.org/L10-1437.pdf) · [OpenAlex](https://openalex.org/W154742286) **Citations:** 14 citations (OpenAlex, 2026-10-14) · [2](https://md.research.elamur.ai/free/en/papers/aliane-2010-al-khalil-arabic-linguistic-ontology/cited-by/) in our library, of the 140,884 papers whose bibliographies we read ## Summary Arabic has few freely available computational resources, and its native grammatical tradition is barely visible to the wider linguistics and NLP communities. The authors describe early work on Al-Khalil, an OWL ontology of Arabic linguistics grounded in Arabic Traditional Grammar (ATG), with particular attention to the Neo-khalilian interpretation of that tradition. They do not build the ontology from scratch. Instead, they attach Arabic grammatical notions to the GOLD linguistic ontology. Construction happens in two stages: - **Manual seed.** Core ATG concepts are taken by hand from a corpus of Neo-khalilian descriptions and linked to GOLD categories in Protégé-OWL. - **Statistical enrichment.** A Python extractor finds repeated text segments after segmentation, light stemming and stop-word removal. An expert then approves the candidate concepts and relations it proposes. Concepts and their relations are modelled as conceptual graphs. The paper reports progress and a roadmap; it gives no evaluation figures. Its value is in showing how a resource-poor language can reuse a shared linguistic ontology to support future lexicons, IR, MT and learning tools. ## Key points - The project is named after the grammarian Al-Khalil Ibn Ahmad Alfarahidi, whose phonetically ordered dictionary, Kitab al-Ayn, the authors regard as an early ontology of Arabic. - The ontology is built on GOLD. Arabic concepts sit under GOLD's root Entity, split into Abstract or Object. Examples include qiyās, kalima, ʿāmil/maʿmūl, fāʿil, mafʿūl and the verb tense schemes. - The enrichment step uses the repeated segments method, with segmentation, light stemming and stop-word filtering as preprocessing. It is implemented in Python, and an expert validates every output. - The plan has seven steps, from scoping to online release, evaluation and applications. Only the first four were done at publication time, and the ontology had not yet been released. - Future work includes: - a Neo-khalilian "community of practice" subontology with its own namespace prefix, alongside forms such as gold:noun and hpsg:noun; - links to the Algerian Arabic treasury corpus project. ## Interesting ideas - Local, tradition-specific categories are placed under a general upper ontology rather than kept as an isolated taxonomy, so they remain interoperable with other frameworks. - Competing theories keep their own namespace-prefixed classes for "the same" notion (gold:noun vs hpsg:noun vs ATG:noun), and these classes are linked rather than merged. - Cheap statistics (repeated segments over lightly stemmed, stop-word-filtered text) propose candidate concepts, but a human gate decides what enters the resource. - Hierarchical is-a links and non-hierarchical relations are modelled explicitly and separately in conceptual graphs, rather than treating the ontology as a bare taxonomy. - The seed effort is spent first on concepts that the general ontology lacks, rather than re-encoding what already exists. ## For Mova How these ideas could serve Mova, our small open language model — its files, stages and tests: - **I1** (world): Mova's own world categories (holdings, states, measures) could each be anchored to a WordNet/Wikidata upper node, so every inference step can cite a shared parent concept. - **I2** (tree): UD dialect conversion could keep labels from each treebank scheme in separate namespaces with explicit mapping links, making every conversion decision traceable. - **I3** (learn): recurring multiword expressions mined from corpora could be offered as candidate frame triggers or lexicon entries, admitted only after LLM-teacher or witness agreement. - **I4** (world): the compiled knowledge layer could keep typed non-taxonomic relations (part-of, causes, used-for) apart from is-a, giving the reasoner distinct, explainable edge types. - **I5** (world): when extending the ontology for fables and school tests, prioritise domain notions missing from WordNet/FrameNet instead of duplicating existing synsets. *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: [Linguistics & languages](https://md.research.elamur.ai/free/en/shelves/linguistics/) Topics: [🕸️ Knowledge graphs & ontologies](https://md.research.elamur.ai/free/en/topics/knowledge-graphs/) · [🐪 Semitic languages](https://md.research.elamur.ai/free/en/topics/semitic-languages/) ## Institutions - [Centre de Recherche sur l'Information Scientifique et Technique](https://md.research.elamur.ai/free/en/labs/centre-de-recherche-sur-l-information-scientifique-et-technique/) — Research institute, Algiers, Algeria · 2 works · 32 citations - [University of Sciences and Technology Houari Boumediene](https://md.research.elamur.ai/free/en/universities/university-of-sciences-and-technology-houari-boumediene/) — University, Algiers, Algeria · 3 works · 23 citations Also on the byline: [University of the Sciences](https://ror.org/048gmay44). ## Cite Cite as: Hassina Aliane, Zaia Alimazighi and Ahmed Cherif Mazari. 2010. Al –-Khalil : The Arabic Linguistic Ontology Project. Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10). The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @inproceedings{aliane2010al, title = {{Al –-Khalil : The Arabic Linguistic Ontology Project}}, author = {Hassina Aliane, Zaia Alimazighi and Ahmed Cherif Mazari}, booktitle = {Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10)}, year = {2010}, doi = {10.63317/4s7jn7yfoaw5}, url = {https://doi.org/10.63317/4s7jn7yfoaw5} } ``` - [← previous Simultaneous Tokenization and Part-Of-Speech Tagging for Arabic without a Morphological Analyzer](https://md.research.elamur.ai/free/en/papers/kulick-2010-simultaneous-tokenization-part-speech-tagging/) - [next → A Tree Transducer Model for Synchronous Tree-Adjoining Grammars](https://md.research.elamur.ai/free/en/papers/maletti-2010-tree-transducer-model-synchronous-tree/) - [↑ back to papers of 2010](https://md.research.elamur.ai/free/en/papers/2010/page/2/) ## References 7 references, 0 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. Aliane H. (2006) “An ontology based approach for multilingual information retrieval” proceedings of ICTTA 2006. Black, W. and S. Elkateb, H. Rodriguez, H, Alkhalifa, M., Vossen, P., Pease, A. and Fellbaum C.” Introducing the Arabic WordNet Project”, in Proceedings of the Third InternationalWordNet Conference, Sojka, Choi, Fellbaum and Vossen eds. [find](https://scholar.google.com/scholar?q=Aliane+H%2E+%282006%29+%E2%80%9CAn+ontology+based+approach+for+multilingual+information+retrieval%E2%80%9D+proceedings+of+ICTTA+2006%2E+Black%2C+W%2E+and+S%2E+Elkateb%2C+H%2E+Rodriguez%2C+H%2C+Alkhalifa%2C+M%2E%2C+Vossen%2C+P%2E%2C+Pease%2C+A%2E+and+Fell) 2. Daoud M &al (2009)“Collaborative construction of Arabic lexical resources” 2 nd international conference on Arabic language resources and tools, cairo. [find](https://scholar.google.com/scholar?q=Daoud+M+%26al+%282009%29%E2%80%9CCollaborative+construction+of+Arabic+lexical+resources%E2%80%9D+2+nd+international+conference+on+Arabic+language+resources+and+tools%2C+cairo%2E) 3. Dichy, J. and A. Braham, S. Ghazali, M. Hassoun (2002) “ La base de connaissances linguistiques DIINAR.1” , Proceedings of the International Symposium on The Processing of Arabic. [find](https://scholar.google.com/scholar?q=Dichy%2C+J%2E+and+A%2E+Braham%2C+S%2E+Ghazali%2C+M%2E+Hassoun+%282002%29+%E2%80%9C+La+base+de+connaissances+linguistiques+DIINAR%2E1%E2%80%9D+%2C+Proceedings+of+the+International+Symposium+on+The+Processing+of+Arabic%2E) 4. Farrar, S. and T. Langendoen (2003) “A linguistic ontology for the semantic web” Glot International Vol 7, N o 3, March 2003”, (P 97-100) NLP tools Arabic lexicons Other arabic databases Web based learning applications MT applications Farrar S. (2003) «An ontological account of linguistics: Extending SUMO with GOLD." Proceedings of the 2003 IEEE International Conference on Natural Language Processing and Knowledge Engineering. [find](https://scholar.google.com/scholar?q=Farrar%2C+S%2E+and+T%2E+Langendoen+%282003%29+%E2%80%9CA+linguistic+ontology+for+the+semantic+web%E2%80%9D+Glot+International+Vol+7%2C+N+o+3%2C+March+2003%E2%80%9D%2C+%28P+97%2D100%29+NLP+tools+Arabic+lexicons+Other+arabic+databases+Web+based+lea) 5. Magnini, B. and S. Speranza (2002) “Merging global and Specialized Linguistic Ontologies”. Proceedings of Ontolex 2002 pp. 43-48. [find](https://scholar.google.com/scholar?q=Magnini%2C+B%2E+and+S%2E+Speranza+%282002%29+%E2%80%9CMerging+global+and+Specialized+Linguistic+Ontologies%E2%80%9D%2E+Proceedings+of+Ontolex+2002+pp%2E+43%2D48%2E) 6. Fensel D. (2000): Ontologies: Silver Bullet for Knowledge Management and Electronic Commerce, URL:[http://www.cs.vu.nl/%7Edieter/ftp/paper/silverbu](http://www.cs.vu.nl/%7Edieter/ftp/paper/silverbu) llet.pdf Graham W. (2007) “an OWL Ontology for HPSG” proceeding of the ACL 2007 demo and poster sessions, 169-172. [↗](http://www.cs.vu.nl/%7Edieter/ftp/paper/silverbu) 7. Gruber T. (2000), “What is an Ontology?” URL: Http:// www-ksl.stanford.edu/kst/what-is-an-ontology.html [find](https://scholar.google.com/scholar?q=Gruber+T%2E+%282000%29%2C+%E2%80%9CWhat+is+an+Ontology%3F%E2%80%9D+URL%3A+Http%3A%2F%2F+www%2Dksl%2Estanford%2Eedu%2Fkst%2Fwhat%2Dis%2Dan%2Dontology%2Ehtml)