The present work aims at automatically classifying Italian idiomatic and non-idiomatic phrases with a neural network model under constrains of data scarcity. Results are discussed in com- parison with an existing unsupervised model devised for idiom type detection and a similar supervised classifier previously trained to detect metaphorical bigrams. The experiments suggest that the distributional context of a given phrase is sufficient to carry out idiom type identifi- cation to a satisfactory degree, with an increase in performance when input phrases are filtered according to human-elicited idiomaticity ratings collected for the same expressions. Crucially, employing concatenations of single word vectors rather than whole-phrase vectors as training input results in the worst performance for our models, differently from what was previously registered in metaphor detection tasks.
Finding the Neural Net: Deep-learning Idiom Type Identification from Distributional Vectors
Alessandro LenciUltimo
2018-01-01
Abstract
The present work aims at automatically classifying Italian idiomatic and non-idiomatic phrases with a neural network model under constrains of data scarcity. Results are discussed in com- parison with an existing unsupervised model devised for idiom type detection and a similar supervised classifier previously trained to detect metaphorical bigrams. The experiments suggest that the distributional context of a given phrase is sufficient to carry out idiom type identifi- cation to a satisfactory degree, with an increase in performance when input phrases are filtered according to human-elicited idiomaticity ratings collected for the same expressions. Crucially, employing concatenations of single word vectors rather than whole-phrase vectors as training input results in the worst performance for our models, differently from what was previously registered in metaphor detection tasks.File | Dimensione | Formato | |
---|---|---|---|
IJCoL04_01-03_Bizzoni-Senaldi-Lenci.pdf
accesso aperto
Descrizione: Articolo principale
Tipologia:
Versione finale editoriale
Licenza:
Creative commons
Dimensione
156.91 kB
Formato
Adobe PDF
|
156.91 kB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.