Home |  English version |  Mappa |  Commenti |  Sondaggio |  Staff |  Contattaci Cerca nel sito  
Istituto di linguistica computazionale "Antonio Zampolli"

Torna all'elenco Contributi in rivista anno 2018

Contributo in rivista

Tipo: Articolo in rivista

Titolo: Deep Learning of Inflection and the Cell-Filling Problem

Anno di pubblicazione: 2018

Formato: Elettronico

Autori: Cardillo, F.A.; Ferro, M.; Marzi, C.; Pirrelli, V.

Affiliazioni autori: ILC-CNR; ILC-CNR; ILC-CNR; ILC-CNR;

Autori CNR:

  • FRANCO ALBERTO CARDILLO
  • MARCELLO FERRO
  • CLAUDIA MARZI
  • VITO PIRRELLI

Lingua: inglese

Abstract: Machine learning offers two basic strategies for morphology induction: lexical segmentation and surface word relation. The first approach assumes that words can be segmented into morphemes. Inferring a novel inflected form requires identification of morphemic constituents and a strategy for their recombination. The second approach dispenses with segmentation: lexical representations form part of a network of associatively related inflected forms. Production of a novel form consists in filling in one empty node in the network. Here, we present the results of a task of word inflection by a recurrent LSTM network that learns to fill in paradigm cells of incomplete verb paradigms. Although the task does not require morpheme segmentation, we show that accuracy in carrying out the inflection task is a function of the model's sensitivity to paradigm distribution and morphological structure.

Lingua abstract: inglese

Pagine da: 57

Pagine a: 75

Pagine totali: 21

Rivista:

Italian Journal of Computational Linguistics
Paese di pubblicazione: Italia
Lingua:
ISSN: 2499-4553

Numero volume: 4

Numero fascicolo: 1

Referee: Sė: Internazionale

Stato della pubblicazione: Published version

Parole chiave:

  • Deep Learning
  • LSTM
  • Cell-Filling Problem

URL: https://www.aaccademia.it/scheda-libro?aaref=1257

Strutture CNR:

 
Torna indietro Richiedi modifiche Invia per email Stampa
Home Il CNR  |  I servizi News |   Eventi | Istituti |  Focus