The Malagasy language in the digital age

Joro Ny Aina Ranaivoarison (1)

1 CIRAM

The creation of useful tools such as spell checkers, or machine translation systems, which would introduce less-resourced languages into the era of new technology and encourage users to use them more, is usually the work of specialists of Natural Language Processing (NLP). For Malagasy, an agglutinative language, the collaboration between specialists of NLP and linguists is required. This paper surveys tools and resources that have been constructed for Malagasy, and, among others, a project based on the DELA framework to construct NLP dictionaries of Malagasy by using conventional dictionaries and converting them into a structured, but readable and manually updatable resource usable by Unitex for morphological analysis. We report on the ongoing construction of an NLP dictionary of simple words (nouns, adjectives, adverbs, grammatical words) with the same DELA methodology and we describe the next steps required.

Mots clés: Less-Resourced Language; Malagasy; NLP dictionary; transducer; morphology; stem class; affix class; nouns; dictionary; e-dictionary; language resource; Unitex

Domaines: Traitement du texte et du document; Linguistique

Joro Ny Aina Ranaivoarison. The Malagasy language in the digital age: Challenges and perspectives. Language and Technology Conference, University Adam Mickiewicz, Nov 2015, Poznań, Poland. pp.299-303. ⟨hal-01237509⟩