Consiglio Nazionale delle Ricerche

Tipo di prodottoContributo in atti di convegno
TitoloWord Processing for Arabic Language: A reappraisal of morphology induction through adaptive memory self-organisation strategies
Anno di pubblicazione2014
FormatoElettronico
Autore/iMarzi, Claudia; Nahli, Ouafae; Ferro, Marcello
Affiliazioni autoriInstitute for Computational Linguistics - National Research Council (ILC-CNR, Pisa)
Autori CNR e affiliazioni
  • OUAFAE NAHLI
  • CLAUDIA MARZI
  • MARCELLO FERRO
Lingua/e
  • inglese
AbstractModelling the mental lexicon focuses on processing and storage dynamics, since 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 identifying morphological formatives within morphologically complex word forms. 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 stored word forms, and to high accuracy rates in generalising knowledge of stored words to unknown forms.
Lingua abstractinglese
Altro abstract-
Lingua altro abstract-
Pagine da241
Pagine a247
Pagine totali7
Rivista-
Numero volume della rivista-
Serie/Collana-
Titolo del volumeIEEE Conference Publications - Catalog Number: CFP1467R-ART
Numero volume della serie/collana-
Curatore/i del volumeM. El Mohajir, M. Al Achhab, M. Chahhou, A. Mounir, B. El Mohajir, V. Pirrelli, A. Zarghili, M. ElFar
ISBN978-1-4799-5979-2
DOI10.1109/CIST.2014.7016626
Editore
  • IEEE, New York (Stati Uniti d'America)
Verificato da refereeSì: Internazionale
Stato della pubblicazionePublished version
Indicizzazione (in banche dati controllate)
  • PUMA (Codice:2014-A2-006)
Parole chiaveNon-concatenative morphological structure, lexical storage and access, SOMs, word recoding and processing, adaptive strategies, morphology
Link (URL, URI)http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=7016626&punumber%3D6996097
Titolo convegno/congressoThird IEEE International Colloquium in Information Science and Technology (CIST)
Luogo convegno/congressoTetuan (Morocco)
Data/e convegno/congresso20-22/10/2014
RilevanzaInternazionale
RelazioneContributo
Titolo parallelo-
Note/Altre informazioni"Best Doctoral Paper Award" consegnato in occasione della comunicazione
Strutture CNR
  • ILC — Istituto di linguistica computazionale "Antonio Zampolli"
Moduli CNR
    Progetti Europei-
    Allegati
    • Book of Abstract
      Descrizione: Book of Abstract
    • Conference oral presentation
      Descrizione: Conference oral presentation
    • IEEE Xplore Digital Library
      Descrizione: IEEE Xplore Digital Library