Tipo di prodotto | Articolo in rivista |
---|---|
Titolo | Deep Learning of Inflection and the Cell-Filling Problem |
Anno di pubblicazione | 2018 |
Formato | Elettronico |
Autore/i | Cardillo, F.A.; Ferro, M.; Marzi, C.; Pirrelli, V. |
Affiliazioni autori | ILC-CNR; ILC-CNR; ILC-CNR; ILC-CNR; |
Autori CNR e affiliazioni |
|
Lingua/e |
|
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 |
Altro abstract | - |
Lingua altro abstract | - |
Pagine da | 57 |
Pagine a | 75 |
Pagine totali | 21 |
Rivista | Italian Journal of Computational Linguistics Paese di pubblicazione: Italia ISSN: 2499-4553 Titolo chiave: Italian Journal of Computational Linguistics |
Numero volume della rivista | 4 |
Fascicolo della rivista | 1 |
DOI | - |
Verificato da referee | Sì: Internazionale |
Stato della pubblicazione | Published version |
Indicizzazione (in banche dati controllate) | - |
Parole chiave | Deep Learning, LSTM, Cell-Filling Problem |
Link (URL, URI) | https://www.aaccademia.it/scheda-libro?aaref=1257 |
Titolo parallelo | - |
Data di accettazione | - |
Note/Altre informazioni | - |
Strutture CNR |
|
Moduli CNR | |
Progetti Europei | - |
Allegati |
|
