Refining the Distributional Inclusion Hypothesis for Unsupervised Hypernym Identification
Several unsupervised methods for hypernym detection have been investigated in distributional semantics. Here we present a new approach based on a smoothed version of the distributional inclusion hypothesis. The new method is able to improve hypernym detection after testing on the BLESS dataset.
Guardado en:
Autores principales: | Ludovica Pannitto, Lavinia Salicchi, Alessandro Lenci |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
Accademia University Press
2018
|
Materias: | |
Acceso en línea: | https://doaj.org/article/da6f8ecc065a4a64bb29d283593ac08e |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
Ejemplares similares
-
Event Knowledge in Compositional Distributional Semantics
por: Ludovica Pannitto, et al.
Publicado: (2019) -
Finding the Neural Net: Deep-learning Idiom Type Identification from Distributional Vectors
por: Yuri Bizzoni, et al.
Publicado: (2018) -
Learning Affect with Distributional Semantic Models
por: Lucia C. Passaro, et al.
Publicado: (2017) -
Panta rei: Tracking Semantic Change with Distributional Semantics in Ancient Greek
por: Martina A. Rodda, et al.
Publicado: (2017) -
Determining the Compositionality of Noun-Adjective Pairs with Lexical Variants and Distributional Semantics
por: Marco S. G. Senaldi, et al.
Publicado: (2017)