Comparative Study of Methods Measuring Lexicographic Similarity Among Tamazight Language Variants

  • Ikan MohamedEmail author
  • Abdessamad Jaddar
  • Aissa Kerkour Elmiad
  • Ghizlane Kouaiba
Conference paper
Part of the Learning and Analytics in Intelligent Systems book series (LAIS, volume 7)


In order to contribute to the standardization of the Tamazight language, we study in this article, the linguistic similarity between the different variants of the Tamazight language (Tamazight of Middle Atlas, Tachelhit, and Tarifit) using the most famous distances in the field of automatic natural language processing (NLP): the Jaro-Winkler distance and the Levenshtein distance. The first results from the application of these distances on our own corpus; based on equivalent words (from the lexicographic point of view), show that the similarity between the different variants of the Tamazight language is very obvious. This brings us to confirm the assumptions formulated in terms of linguistic or phonetic equivalence on certain characters or phone.


Tamazight Lexicographic equivalence Distance from Jaro-Winkler Distance from Levenshtein NLP 


  1. 1.
    Ameur, M., Boumalk, A.: (coord) Standardisation de l’amazigh’, Rabat, publication du l’IRCAM (2004)Google Scholar
  2. 2.
    Guerrab, S.: Analyse dialectometrique des parles berbères de kabylie Thèse soutenu en (2014)Google Scholar
  3. 3.
    Kukich, K.: Techniques for automatically correcting words in text. ACM Comput. Surv. 24(4), 377–439 (1992)CrossRefGoogle Scholar
  4. 4.
    Gueddah, H., Yousfi, A., Belkasmi, M.: Introduction of the weight edition errors in the Levenshtein distance. Int. J. Adv. Res. Artif. Intell. 1(5) (2012)Google Scholar
  5. 5.
    Winkler, W.E.: The state of record linkage and current research problems. Technical report, Statistics of Income Division, Internal Revenue Service Publication R99/04 (1999)Google Scholar
  6. 6.
    Levenshtein, V.: Binary codes capable of correcting deletions, insertions and reversals. SOL Phys. Dokl. 10, 707–710 (1996)Google Scholar
  7. 7.
    Pevzner, P.A.: Bio-informatique moléculaire une approche algorithmique collection IRIS, dirigé par Nicolas peuch, Tradiction: Delphine hachez, Springer Editions, October 2006Google Scholar
  8. 8.
    Wanger, R.A., Fisher, M.J.: The string to string correction problem. Commun. ACM 20(10), 168–173 (2014)Google Scholar
  9. 9.
    Heeringa, W.: Measure dialect pronunciation differences using levenshtein distance, These 2004, Université de Groningen (Holland) (2004)Google Scholar
  10. 10.
    Institut royal de la culture amazighe (IRCAM): ouvrage ‘Dictionnaire français tachalh’it et tamazir’t’.Auteur: S cid kaouiGoogle Scholar
  11. 11.
    Institut royal de la culture amazighe (IRCAM): ouvrage ‘Dictionnaire Tarifit-français. Mohamed serhoual, AuteurGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Ikan Mohamed
    • 1
    Email author
  • Abdessamad Jaddar
    • 1
  • Aissa Kerkour Elmiad
    • 2
  • Ghizlane Kouaiba
    • 3
  1. 1.Laboratory MAOUniversity Mohammed 1erOujdaMorocco
  2. 2.Laboratory RIUniversity Mohammed 1erOujdaMorocco
  3. 3.Laboratory AMGNPA, Faculty of ScienceIbn Tofail UniversityKenitraMorocco

Personalised recommendations