Predicting grammatical gender in Nakh languages: Three methods compared

Linguistic Typology at the Crossroads

Abstract

The Nakh languages Chechen and Tsova-Tush each have a five-valued gender system: masculine, feminine, and three “neuter” genders named for their singular agreement forms: B, D and J. Gender assignment in languages is generally analysed as being dependent on both forms and semantics (e.g. Corbett, 1991), with semantics typically prevailing over form (e.g. Bellamy & Wichers Schreur, 2021, Allassonnière-Tang et al., 2021). Most previous studies have considered only binary or tripartite gender systems possessing masculine, feminine, and neuter values. The five-valued system of Nakh thus represents an innovative and insightful case study for analysing gender assignment. In this paper we build on the existing qualitative linguistic analyses of gender assignment in Tsova-Tush (Wichers Schreur, 2021) and apply three machine-learning methods to investigate the weight of form and semantics in predicting grammatical gender in Chechen and Tsova-Tush. The results show that while both form and semantics are helpful for predicting grammatical gender in Nakh, semantics is dominant, which supports findings from existing literature (Allassonnière-Tang, Brown & Fedden, 2021). However, the results also show that the coded semantic information could be further fine-grained to improve the accuracy of the predictions (see also Plaster et al., 2013). In addition, we discuss the implications of the output for our understanding of language-internal and family-internal processes of language change, including how loanwords are integrated from Russian, a three-gender language.

Authors 4

1. Jesse Wichers Schreur Aachen

   Goethe University Frankfurt · Leiden University · École Pratique des Hautes Études

   Affiliation as printed

   EPHE - École Pratique des Hautes Études (4-14 Rue Ferrus, 75014 Paris - France)

   Goethe-Universität Frankfurt am Main (Theodor-W.-Adorno-Platz 1 , 60323 Frankfurt am Main - Germany)

   Universiteit Leiden = Leiden University (Leiden University | 2300 RA Leiden The Netherlands - Netherlands)

2. Marc Allassonnière‐Tang

   Éco-Anthropologie · Musée de l'Homme

   Affiliation as printed

   EA - Éco-Anthropologie (Musée de l’Homme - 17 place du Trocadéro - 75016 Paris - France)

3. Kate Bellamy Aachen

   Leiden University

   Affiliation as printed

   Universiteit Leiden = Leiden University (Leiden University | 2300 RA Leiden The Netherlands - Netherlands)

4. Neige Rochant

   Centre National de la Recherche Scientifique · Université Sorbonne Nouvelle · Langage, langues et cultures d'Afrique · Langues et Civilisations à Tradition Orale

   Affiliation as printed

   LACITO - Langues et civilisations à tradition orale (7, rue Guy Môquet, 94800, VILLEJUIF - France)

   LLACAN - Langage, LAngues et Cultures d'Afrique (Campus CNRS de Villejuif – 7 rue Guy Môquet – 94800 Villejuif - France)

   USN LLD - Université Sorbonne Nouvelle - Paris 3 - UFR Littérature, Linguistique, Didactique (13, rue Santeuil - 75231 Paris Cedex 05 - France)