Morphological study of Albanian words, and processing with NooJ

Odile Piton (1) , Klara Lagji (2)

1 Marin Mersenne - Pour les Mathématiques, l'Informatique et l'Interdisciplinarité
2 Laboratoire de Tirana

We are developing electronic dictionaries and transducers for the automatic processing of the Albanian Language. We will analyze the words inside a linear segment of text. We will also study the relationship between units of sense and units of form. The composition of words takes different forms in Albanian. We have found that morphemes are frequently concatenated or simply juxtaposed or contracted. The inflected grammar of NooJ allows constructing the dictionaries of flexed forms (declensions or conjugations). The diversity of word structures requires tools to identify words created by simple concatenation, or to treat contractions. The morphological tools of NooJ allow us to create grammatical tools to represent and treat these phenomena. But certain problems exceed the morphological analysis and must be represented by syntactical grammars.

Mots clés: natural language processing; inflectional graph; morphological graph; dynamic processing; syntactical grammar; syntactical grammar.; morphological analysis; electronic dictionary; Albanian language

Domaines: Informatique et langage [cs.CL]; Traitement du texte et du document

Odile Piton, Klara Lagji. Morphological study of Albanian words, and processing with NooJ. 2007 NooJ Conference, Jun 2007, Barcelone, Spain. pp.189-205. ⟨hal-00452458⟩