Izvorni znanstveni članak
https://doi.org/10.20532/cit.2016.1002478
AmAMorph: Finite State Morphological Analyzer for Amazighe
Fatima Zahra Nejme
orcid.org/0000-0002-1572-8673
; LRIT, associated unit to the CNRST-URAC n ◦ 29, Mohammed V University, Faculty of Science, Rabat, Morocco
Siham Boulaknadel
; Royal Institute of Amazigh Culture, Rabat, Morocco
Driss Aboutajdine
; Mohammed V University Faculty of Science, Rabat, Morocco
Sažetak
This paper presents AmAMorph, a morphological analyzer for Amazighe language using a system based on the NooJ linguistic development environment. The paper begins with the development of Amazighe lexicons with large coverage formalization. The built electronic lexicons, named ‘NAmLex’, ‘VAmLex’ and ‘PAmLex’ which stand for ‘Noun Amazighe Lexicon’, ‘Verb Amazighe Lexicon’ and ‘Particles Amazighe Lexicon’, link inflectional, morphological, and syntacticsemantic information to the list of lemmas. Automated inflectional and derivational routines are applied to each lemma producing over inflected forms. To our knowledge,AmAMorph is the first morphological analyzer for Amazighe. It identifies the component morphemes of the forms using large coverage morphological grammars. Along with the description of how the analyzer is implemented, this paper gives an evaluation of the analyzer.
Ključne riječi
Amazighe language; Natural Language Processing; NooJ; Lexical Analysis; Inflectional Morphology; Derivational Morphology; Unknown words; Recognition Systems
Hrčak ID:
155090
URI
Datum izdavanja:
25.3.2016.
Posjeta: 1.323 *