The great majority of compositional models in distributional semantics present methods tocompose vectors or tensors in a representation of the sentence. Here we propose to enrich oneof the best performing methods (vector addition, which we take as a baseline) with distributionalknowledge about events. The resulting model is able to outperform our baseline.
Event Knowledge in Compositional Distributional Semantics
Alessandro Lenci
Secondo
2019-01-01
Abstract
The great majority of compositional models in distributional semantics present methods tocompose vectors or tensors in a representation of the sentence. Here we propose to enrich oneof the best performing methods (vector addition, which we take as a baseline) with distributionalknowledge about events. The resulting model is able to outperform our baseline.File in questo prodotto:
| File | Dimensione | Formato | |
|---|---|---|---|
|
pannittoLenci_IJCOL_2019.pdf
accesso aperto
Descrizione: Articolo principale
Tipologia:
Versione finale editoriale
Licenza:
Creative commons
Dimensione
679 kB
Formato
Adobe PDF
|
679 kB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
