Elamur Research⌕
☰
home / papers / 2016 / Arabic WordNet: New Content and New Applications

Arabic WordNet: New Content and New Applications

Paper · 2016 · Yasser Regragui, Lahsen Abouenour, Fettoum Krieche et al.

Summary

Arabic WordNet (AWN) was the first WordNet-style lexicon for Arabic, but it was too small for real applications. The authors had earlier proposed semi-automatic enrichment. That work added YAGO named entities via translation, new verb senses derived from English VerbNet and the Unified Verb Index, hyponymy links between nouns mined from Web snippets with Maximal Frequent Sequences (MFS), and Broken Plural (BP) forms, which are irregular and cannot be produced by morphological patterns.

This paper reports the final step. Three native-speaker lexicographers checked the new nouns, verbs and BPs, and the authors give acceptance rates for each kind of content. They summarise question-answering experiments in which the enriched AWN improved Arabic QA, with C@1 rising from 0.21 to 0.51. They also describe converting the whole resource into the ISO Lexical Markup Framework (LMF), using SAFAR morphological analyzers to fill in missing part-of-speech tags. The outcome is AWN v2, released through the Open Multilingual WordNet. It matters because Arabic NLP now has a larger, standard-format and human-checked lexical resource.

Key points

  • The original AWN had 9,698 synsets and 21,813 MSA words. A later version had 11,269 synsets and 23,841 words, and 6,556 synsets are linked to 659 SUMO concepts.
  • Lexicographers judged each new item in three ways: whether the word is correct, whether it belongs in the synset, and whether the proposed relation holds.
    • About 75% of proposed verbs were accepted: 23% as clear synset members and 52% as "lenient synonymy".
    • Of the MFS-proposed noun hyponymy links, 37% were correct and another 4% turned out to be meronymy or antonymy, giving 41% usable relations.
    • BP forms had the highest success rate, at 91%.
  • In QA, the enriched AWN served both for keyword expansion and as support at the semantic level. C@1 went from 0.21 to 0.51.
  • The LMF conversion (ISO-24613:2008) used the semantics and morphology packages and was done with Java DOM. It left 1,036 entries without a POS tag. SAFAR's analyzers supplied 1,012 tags, of which 24 were wrong and were fixed by hand.
  • The final LMF file contains 56,164 lexical entries, 17,498 word forms and 41,136 synset relations, published as AWN v2 on the Open Multilingual WordNet.

Interesting ideas

  • I1. Reviewers could mark a relation as correct but loose ("lenient"), or relabel a wrong hyponymy link as meronymy or antonymy instead of discarding it, which saves partly-correct machine proposals.
  • I2. The authors measured precision separately for each enrichment source (BP resource 91%, MFS hyponymy 41%), showing how unevenly trustworthy automatic sources can be.
  • I3. What to add was chosen by looking at which words from real questions were missing in the lexicon, so coverage work was driven by observed application failures.
  • I4. Irregular forms that no pattern can derive, like Arabic broken plurals, were stored explicitly as word forms linked to their lemma.
  • I5. Missing POS tags were filled by several morphological analyzers working together, followed by manual review of their output.

For Mova

How these ideas could serve Mova, our small open language model — its files, stages and tests:

  • I1 (world): Our WordNet-derived ontology edges could carry a strict/loose grade, so inference uses loose links only as weaker evidence.
  • I2 (learn): Silver knowledge or rules could be weighted by the measured precision of the source that produced them, rather than all sources being trusted equally.
  • I3 (answer): Logging which words or senses school-test and fable-QA failures hit could rank which lexicon or ontology gaps to fill first.
  • I4 (tokens): Keep English irregular plurals and verb forms as explicit, curated lexicon entries checked before any rule-based lemmatizer, so lemmas stay explainable.
  • I5 (learn): Missing lexical attributes could be filled the same way, by agreement among several taggers, with only the disagreements sent to an LLM teacher or a human.

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

 Institutions

🎓Universitat Politècnica de ValènciaValencia · Spain34 works · 3,575 citations🎓Sidi Mohamed Ben Abdellah UniversityFes · Morocco8 works · 156 citations🎓Mohammed V UniversityRabat · Morocco8 works · 103 citations🎓Ecole Mohammadia d'IngénieursRabat · Morocco4 works · 32 citations

 Fields, topics and concepts

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Computer Science · 18,614 worksArtificial Intelligence · 17,965 worksArts and Humanities · 17,450 worksLanguage and Linguistics · 17,296 works

🧭 Topics 2Research subjects and languages the work is about.Semitic languages · 3,066 worksMorphology · 420 works

Cite

Cite as Yasser Regragui, Lahsen Abouenour, Fettoum Krieche, Karim Bouzoubaa and Paolo Rosso. 2016. Arabic WordNet: New Content and New Applications. Proceedings of the 8th Global WordNet Conference (GWC).

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2016.gwc-1.47

@inproceedings{regragui2016arabic,
  title = {{Arabic WordNet: New Content and New Applications}},
  author = {Yasser Regragui, Lahsen Abouenour, Fettoum Krieche, Karim Bouzoubaa and Paolo Rosso},
  booktitle = {Proceedings of the 8th Global WordNet Conference (GWC)},
  year = {2016},
  doi = {10.18653/v1/2016.gwc-1.47},
  url = {https://doi.org/10.18653/v1/2016.gwc-1.47}
}

References

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

  1. Abbache, A., Barigou, F., Belkredim, F. Z., & Belalem, G. (2014). The Use of Arabic WordNet in Arabic Information Retrieval., International Journal of Information Retrieval Research (IJIRR), 4(3), 54-65. find
  2. Abouenour, L., Bouzoubaa, K., Rosso, P. (2010). An evaluated semantic QE and structure-based approach for enhancing Arabic Q/A. In the Special Issue on Advances in Arabic Language Processing for the IEEE International Journal on Information and Communication Technologies (IJICT), ISSN: 0973-5836, Serial Publications, June 2010. find
  3. Abouenour, L., Bouzoubaa, K., Rosso, P. (2012). ID-RAAQ: New Arabic Question Answering System Based on Query Expansion and Passage Retrieval., CLEF’2012 (Online Working Notes/Labs/Workshop). find
  4. Abouenour, L., Bouzoubaa, K., Rosso, P. (2013). On the Evaluation and Improvement of Arabic WordNet Coverage and Usability. In: Languages Resources and Evaluation, vol. 47, issue 3, pp. 891-917. ↗
  5. Abouenour, L., Nasri, M, Bouzoubaa, K., Kabbaj, A., Rosso, P. (2014). Construction of an ontology for intelligent Arabic QA systems leveraging the Conceptual Graphs representation. Journal of Intelligent and Fuzzy Systems. ↗
  6. Al Khalifa, M., & Rodríguez, H. (2009). Automatically extending NE coverage of Arabic WordNet using Wikipedia. In Proceedings of the 3rd international conference on Arabic language processing CITALA'09, May, Rabat, Morocco. find
  7. Al-Zoghby, A. M., & Shaalan, K. (2015). Conceptual Search for Arabic Web Content. In Computational Linguistics and Intelligent Text Processing (pp. 405-416). Springer International Publishing. find
  8. Baldwin, T., Pool, P., & Colowick, S. M. (2010). PanLex and LEXTRACT: Translating all words of all languages of the world. In Proceedings of Coling 2010, Demonstration Volume, (pp. 37– 40), Beijing. find
  9. Benajiba, Y., & Rosso, P. (2008). Arabic Named Entity Recognition using Conditional Random Fields. In: Proc. Workshop on HLT & NLP within the Arabic world. Arabic Language and local languages processing: Status Updates and Prospects, 6th Int. Conf. on Language Resources and Evaluation, LREC-2008, Marrakech, Morocco, May 26-31. find
  10. Benajiba, Y., Diab M., & Rosso, P. (2009). Arabic Named Entity Recognition: A Feature-Driven Study. In: IEEE Transactions on Audio, Speech and Language Processing, vol. 15, num. 5. Special Issue on Processing Morphologically Rich Languages, pp. 926-934. 2009. ↗
  11. Black, W., Elkateb, S., Rodriguez, H, Alkhalifa, M., Vossen, P., Pease, A., & Fellbaum, C. (2006). Introducing the Arabic WordNet project. In Proceedings of the third international WordNet conference. Sojka, Choi: Fellbaum & Vossen (eds). Black, W., Elkateb, S., Rodriguez, H, Alkhalifa, M.,Vossen, P., Pease, A., and Fellbaum, C., (2006). Introducing the Arabic WordNet Project. In Proceedings of the Third International Word-Net Conference, Fellbaum and Vossen (eds). find
  12. Boudabous, M.M., Chaâben, N., Khedher, N., Hadrich Belguith, L., Sadat, F. (2013). Arabic WordNet semantic relations enrichment through morpho-lexical patterns, The First International Conference on Communications, Signal Processing, and their Applications (ICCSPA’13), Sharjah, UAE, February 12–14. find
  13. Bouhriz, N., Benabbou, F., & Benlahmer, H. (2015). Text Concepts Extraction based on Arabic WordNet and Formal Concept Analysis International Journal of Computer Applications (0975 – 8887) Volume 111 – No 16, February. find
  14. Cavalli-Sforza, V., Saddiki, H., Bouzoubaa, K., Abouenour, L., Maamouri, M., & Goshey, E. (2013). Bootstrapping a wordnet for an arabic dialect from other wordnets and dictionary resources. In Computer systems and applications (aiccsa), 2013 acs international conference on (pp. 1–8). find
  15. Clark, P., & Fellbaum, C., & Hobbs, J. (2008). Using and extending WordNet to support question-answering. In: Proceedings of the Fourth Global WordNet Conference, University of Szeged, Hungary, pp. 111–119. COLING, pages 42.488. Del Gratta, R.; Nahli, O., Enhancing Arabic WordNet with the use of Princeton WordNet and a bilingual dictionary, in Information Science and Technology (CIST), 2014 Third IEEE International Colloquium in , vol., no., pp.278-284, 20-22 Oct. 2014. find
  16. El Amine, M. A. (2009). Vers une interface pour l’enrichissement des requêtes en arabe dans un système de recherche d’information. In Proceedings of the 2nd conférence internationale sur l'informatique et ses applications (CIIA'09), May 3-4, Saida, Algeria. find
  17. Elghamry, K. (2008). Using the Web in building a corpus-based hypernymy-hyponymy lexicon with hierarchical structure for Arabic. Faculty of computers and information (pp. 157-165). Elkateb, S., Black, W., Vossen, P., Farwell, D., Rodríguez, H., Pease, A., & Al khalifa, M. (2006). Arabic WordNet and the challenges of Arabic. In Proceedings of Arabic NLP/MT conference, London, U.K.
  18. Elkateb, S., Black, W., Rodriguez, H., Alkhalifa, M., Vossen, P., Pease, A., and Fellbaum, C., (2006). Building a WordNet for Arabic. In Proceedings of the Fifth International Conference on Language Resources and Evaluation, Genoa, Italy. Elkateb, S., Black, W., Rodriguez, H., Alkhalifa, M.,Vossen, P., Pease, A., and Fellbaum, C., (2006). Building a WordNet for Arabic. In Proceedings of the Fifth International Conference on Language Resources and Evaluation, Genoa, Italy. Fellbaum, C. (ed.), WordNet: An electronic lexical database. Cambridge, MA: MIT Press, 1998.
  19. Francis Bond and Kyonghee Paik (2012). A survey of wordnets and their licenses In Proceedings of the 6th Global WordNet Conference (GWC 2012). Matsue. 64–71. find
  20. Francopoulo G., Bel N., George M., Calzolari N., Monachini M., Pet M., Soria C. 2007 Lexical Markup Framework: ISO standard for semantic information in NLP lexicons. GLDV (Gesellschaft für linguistische Datenverarbeitung), Tubingen García-Blasco, S., Danger, R., & Rosso, P. (2010). Drug-Drug interaction detection: A new approach based on maximal frequent sequences. Sociedad Española para el Procesamiento del Lenguaje Natural, SEPLN, 45, 263-266. find
  21. García-Hernández, R. A. (2007). Algoritmos para el descubrimiento de patrones secuenciales maximales. Ph.D. thesis, INAOE. September, Mexico. find
  22. García-Hernández, R. A. (2007). Algoritmos para el descubrimiento de patrones secuenciales maximales. Ph.D. thesis, INAOE. September, Mexico. find
  23. García-Hernández, R. A., Martínez Trinidad, J. F., & Carrasco-ochoa, J. A. (2010). Finding maximal sequential patterns in text document collections and single documents. Informatica, 34(1), 93-101. find
  24. Jaafar, Y., & Bouzoubaa, K. Arabic Natural Language Processing from Software Engineering to Complex Pipelines Cicling Cairo, Egypt 4/ 2015. find
  25. Karkar, A., Alja'am, J. M., Eid, M., & Sleptchenko, A. (2015). E-LEARNING MOBILE APPLICA-TION FOR ARABIC LEARNERS. Journal of Educational & Instructional Studies in the World, 5(2). find
  26. Kipper-Schuler, K. (2006). VerbNet: A broad-coverage, comprehensive verb lexicon. Ph.D Thesis. ↗
  27. Kreaa, A., Ahmad S Ahmad and Kassem Kabalan (2014). Arabic Words Stemming approach using Arabic WordNet. International Journal of Data Mining & Knowledge Management Process (IJDKP) Vol.4, No.6, November 2014. Mousser, J. A Large Coverage Verb Lexicon For Arabic. In: Proceedings of the 7th conference on International Language Resources and Evaluation (LREC) (2010), Valetta, Malta. Mousser, J. Classifying Arabic Verbs Using Sibling Classes. In: Proceeding of the International Conference on Computational Semantics (IWCS) (2011), Oxford, UK. ↗
  28. Niles, I., & Pease, A. (2001). Towards a standard upper ontology. In Proceedings of FOIS-2 (pp. 2– 9), Ogunquit, Maine. find
  29. Niles, I., & Pease, A. (2003). Linking lexicons and ontologies: Mapping WordNet to the Suggested Upper Merged Ontology. In Proceedings of the 2003 international conference on information and knowledge engineering, Las Vegas, Nevada. find
  30. Reyes A., Rosso P., Buscaldi D. (2010). Finding Humour in the Blogosphere: The Role of WordNet Resources. In: Proc. 5th Global WordNet Int. Conf., GWN-2010, Bombay, India, January 31-February 4. find
  31. Rodriguez, H., Farwell, D., Farreres, J., Bertran, M., Alkhalifa, M., & Martí, A. (2008a). Arabic WordNet: Semi-automatic extensions using Bayesian Inference. In Proceedings of the the 6th Conference on Language Resources and Evaluation LREC2008, May, Marrakech, Morocco.
  32. Rodriguez, H., Farwell, D., Farreres, J., Bertran, M., Alkhalifa, M., Mart., M., Black, W., Elkateb, S., Kirk, J., Pease, A., Vossen, P., & Fellbaum, C. (2008b). Arabic WordNet: Current state and future extensions. In Proceedings of the fourth global WordNet conference, January 22-25, Szeged, Hungary. find
  33. Rodríguez, R., Farwell, D., Farreres, J., Bertran, M., Alkhalifa, M., Martí, M.A., Black, W., Elkateb, S., Kirk, J., Pease, A., Vossen, P., and Fellbaum, C., (2008). Arabic WordNet: Current State and Future Extensions.Proceedings of The Fourth Global WordNet Sharaf, A. M. (2009). The Qur'an annotation for text mining. First year transfer report. School of Computing, Leeds University. December. find
  34. Sidrine, S., Y. Souteh, K. Bouzoubaa and T. Loukili, SAFAR: vers une Plateforme Ouverte pour le Traitement Automatique de la Langue Arabe. In: Proceeding of the 6th Conference of Intelligent Systems: Theory and Applications SITA (2010), May, Rabat, Morocco. Souteh, Y., & Bouzoubaa, K. SAFAR platform and its morphological layer, In Proceeding of the Eleventh Conference on Language Engineering ESOLEC’2011, Cairo, Egypt, 14/ 12/ 2011. find
  35. Sowa J. F. (1984). Conceptual Structures: Information Processing in Mind and Machine. Addison-Wesley Company. Sowa, F. Conceptual Structures: Information Processing in Mind and Machine, 1984, Addison-Wesley Company. Suchanek, F. M., Kasneci, G., Weikum, G.: YAGO: a core of semantic knowledge unifying WordNet and Wikipedia. In Proc. of the 16th WWW, pp. 697-706 (2007). find
  36. Suhad A. Yousif, Venus W. Samawi, Islam Elkabani and Rached Zantout (2015). Enhancement of Arabic Text Classification Using Semantic Relations of Arabic WordNet. Journal of Computer Science, Volume 11, Issue 3, Pages 498-509. ↗
  37. Sutcliffe, R., A. Peñas, E. Hovy, P. Forner, A. Rodrigo and C. Forascu (2013). Overview of QA4MRE Main Task, CLEF. Vossen P. (ed). EuroWordNet, A Multilingual Database with Lexical Semantic Networks. find
  38. Kluwer Academic Publishers, 1999, The Netherlands. find
  39. Vossen, P. (ed). (1998). EuroWordNet, a multilingual database with lexical semantic networks. Kluwer Academic Publishers, The Netherlands. ↗

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/regragui-2016-arabic-wordnet-new-content-new/