Distributional semantics has been extended to phrases and sentences by means of composition operations. We look at how these operations affect similarity measurements, showing that similarity equations of an important class of composition methods can be decomposed into operations performed on the subparts of the input phrases. This establishes a strong link between these models and convolution kernels.
Zanzotto, F.m., Ferrone, L., Baroni, M. (2015). When the whole is not greater than the combination of its parts: A “decompositional” look at compositional distributional semantics. COMPUTATIONAL LINGUISTICS, 41(1), 165-173 [10.1162/COLI_a_00215].
When the whole is not greater than the combination of its parts: A “decompositional” look at compositional distributional semantics
ZANZOTTO, FABIO MASSIMO;
2015-01-01
Abstract
Distributional semantics has been extended to phrases and sentences by means of composition operations. We look at how these operations affect similarity measurements, showing that similarity equations of an important class of composition methods can be decomposed into operations performed on the subparts of the input phrases. This establishes a strong link between these models and convolution kernels.| File | Dimensione | Formato | |
|---|---|---|---|
|
coli_a_00215.pdf
solo utenti autorizzati
Licenza:
Copyright dell'editore
Dimensione
111.46 kB
Formato
Adobe PDF
|
111.46 kB | Adobe PDF | Visualizza/Apri Richiedi una copia |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
