Consiglio Nazionale delle Ricerche

Tipo di prodottoArticolo in rivista
TitoloArabic word processing and morphology induction through adaptive memory self-organisation strategies
Anno di pubblicazione2017
FormatoElettronico
Autore/iMarzi, C.; Ferro, M.; Nahli, O.
Affiliazioni autoriInstitute for Computational Linguistics - National Research Council
Autori CNR e affiliazioni
  • OUAFAE NAHLI
  • CLAUDIA MARZI
  • MARCELLO FERRO
Lingua/e
  • inglese
AbstractAim of the present study is to model the human mental lexicon, by focussing on storage and processing dynamics, as lexical organisation relies on the process of input recoding and adaptive strategies for long-term memory organisation. A fundamental issue in word processing is represented by the emergence of the morphological organisation level in the lexicon, based on paradigmatic relations between fully-stored word forms. Morphology induction can be defined as the task of perceiving and identifying morphological formatives within morphologically complex word forms, as a function of the dynamic interaction between lexical representations and distribution and degrees of regularity in lexical data. In the computational framework we propose here (TSOMs), based on Self-Organising Maps with Hebbian connections defined over a temporal layer, the identification/perception of surface morphological relations involves the alignment of recoded representations of morphologically-related input words. Facing a non-concatenative morphology such as the Arabic inflectional system prompts a reappraisal of morphology induction through adaptive organisation strategies, which affect both lexical representations and long-term storage. We will show how a strongly adaptive self-organisation during training is conducive to emergent relations between word forms, which are concurrently, redundantly and competitively stored in human mental lexicon, and to generalising knowledge of stored words to unknown forms.
Lingua abstractinglese
Altro abstract-
Lingua altro abstract-
Pagine da179
Pagine a188
Pagine totali10
RivistaJournal of King Saud University. Computer and information sciences (Online)
Attiva dal 2011
Editore: Elsevier - Amsterdam
Paese di pubblicazione: Paesi Bassi
Lingua: inglese
ISSN: 2213-1248
Titolo chiave: Journal of King Saud University. Computer and information sciences (Online)
Titolo proprio: Journal of King Saud University. (Online)
Numero volume della rivista29
Fascicolo della rivista2
DOI10.1016/j.jksuci.2016.11.006
Verificato da refereeSì: Internazionale
Stato della pubblicazionePublished version
Indicizzazione (in banche dati controllate)-
Parole chiaveNon-concatenative morphological structure, Lexical storage and access, Topological alignment, Synchronisation, Self-Organising Maps
Link (URL, URI)http://www.sciencedirect.com/science/article/pii/S1319157816301148
Titolo parallelo-
Data di accettazione13/11/2016
Note/Altre informazioniSpecial issue on "Arabic Natural Language Processing: Models, Systems and Applications" edited By Vito Pirrelli and Arsalane Zarghili
Strutture CNR
  • ILC — Istituto di linguistica computazionale "Antonio Zampolli"
Moduli CNR
    Progetti Europei-
    Allegati
    • Arabic word processing and morphology induction through adaptive memory self-organisation strategies
      Descrizione: Marzi_et_al_2017_published