Formalization of Malagasy conjugation

📅 2026-05-26
📈 Citations: 0
Influential: 0
📄 PDF

career value

150K/year
🤖 AI Summary
This study addresses the lack of structured morphological analysis tools for Malagasy verbs, which exhibit complex conjugation patterns and affix combinations. Building upon the Unitex platform, the work presents the first systematic formalization of inflectional rules for simple Malagasy verbs, resulting in an electronic dictionary comprising 349 finite-state transducers—78 dedicated to stem generation and 271 to morphological analysis. The system employs a feature-based morphological representation that enables accurate identification of conjugated verb forms and generation of stem allomorphs. Designed with readability and extensibility in mind, this resource establishes a foundational infrastructure for future development of Malagasy language resources and computational linguistics research.
📝 Abstract
This paper reports the core linguistic work performed to construct a dictionary-based morphological analyser for Malagasy simple verbs. It uses the Unitex platform and comprised the contruction of an electronic dictionary for Malagasy simple verbs. The data is encoded on the basis of morphological features. The morphological variations of verb stems and their combination with inflectional affixes are formalized in finite-state transducers represented by editable graphs. 78 transducers allow Unitex to generate a dictionary of allomorphs of stems. 271 other transducers are used by the morphological analyser of Unitex to recognize the stem and the affixes in conjugated verbs. The design of the dictionary and transducers prioritizes readability, so that they can be extended and updated by linguists.
Problem

Research questions and friction points this paper is trying to address.

Malagasy conjugation
morphological analyser
verb stems
inflectional affixes
finite-state transducers
Innovation

Methods, ideas, or system contributions that make the work stand out.

morphological analyser
finite-state transducers
Malagasy verbs
Unitex platform
allomorph generation
🔎 Similar Papers
2017-08-30Conference on Empirical Methods in Natural Language ProcessingCitations: 24