Logo Lanfrica
  • Accueil
  • Atlas
  • Analyses
  • Documentation
  • Sign in

© 2026 Lanfrica. Tous droits réservés. Tous les droits d'auteur des ressources affichées sur le site Web Lanfrica appartiennent aux détenteurs de droits d'auteur d'origine, sauf indication contraire explicite.

Describing Morphologically-rich Languages using Metagrammars: a Look at Verbs in Ikota

Domaine:

natural language processing

Type de record:

papersoftware
Créateur:
DucMagParPet
Éditeur:
LabLabG. G-M
Éditeur:
CCSDEur
Hôte:avatar
Available on-line at International audience In this paper, we show how the concept of metagrammar originally introduced by Candito (1996) to design large Tree-Adjoining Grammars describing the syntax of French and Italian, can be used to describe the morphology of Ikota, a Bantu language spoken in Gabon. Here, we make use of the expressivity of the XMG (eXtensible MetaGrammar) formalism to describe the morphological variations of verbs in Ikota. This XMG specification captures generalizations over these morphological variations. In order to produce the inflected forms, one can compile the XMG specification, and save the resulting electronic lexicon in an XML file, thus favorising its reuse in dedicated applications.

Visit

hal.science

Languages

Kota

Tags

[INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL][SHS.LANGUE]Humanities and Social Sciences/Linguistics

Licenses

https://about.hal.science/hal-authorisation-v1/info:eu-repo/semantics/OpenAccess

Similaires

Translating into Morphologically Rich Languages with Synthetic PhrasesA context-aware word embedding model for morphologically rich languages using Sesotho sa Leboa as a case studyMachine Translation for Morphologically Rich Low-Resourced South African LanguagesStructural Biases for Improving Transformers on Translation into Morphologically Rich LanguagesLeveraging Semantic Diffusion for Polysemous Word Disambiguation in Morphologically Rich Low-resourced LanguagesUTER: Capturing the Human Touch in Evaluating Morphologically Rich and Low-Resource Languages

Translating into Morphologically Rich Languages with Synthetic Phrases

Translation into morphologically rich languages is an important but recalcitrant problem in MT. W

A context-aware word embedding model for morphologically rich languages using Sesotho sa Leboa as a case study

Meaning conflation deficiency (MCD) is a major issue in natural language processing (NLP) to improve

Machine Translation for Morphologically Rich Low-Resourced South African Languages

Structural Biases for Improving Transformers on Translation into Morphologically Rich Languages

Machine translation has seen rapid progress with the advent of Transformer-based models. These model

Leveraging Semantic Diffusion for Polysemous Word Disambiguation in Morphologically Rich Low-resourced Languages

Word Sense Disambiguation (WSD) remains one of the most challenging problems in Natural Language Pro

UTER: Capturing the Human Touch in Evaluating Morphologically Rich and Low-Resource Languages