: Vocabulario de PLN: convolution kernel

NLP methods and tools > signal processing > convolution kernel

convolution kernel

Convolution kernels (CK) are special kernel functions. (Wiegand & Klakow, 2012)
Convolution kernels support the modeling of complex syntactic information in machinelearning tasks. (Tu, He, Foster, van Genabith, Liu & Lin, 2012)
In particular we used RST-style discourse parse trees which we compared using convolution kernels. (Joty, Guzmán, Màrquez & Nakov, 2014)
The number of convolution kernels is 32 in the first layer and 16 in the second layer. (Tao, Wu, Xu, Hu, Zhao & Yan, 2019)
We found that relation extraction can benefit from increasing the feature space through convolution kernel and introducing bias towards more syntactically meaningful feature space. (Wang, 2008)

http://data.loterre.fr/ark:/67375/8LP-XF6VBQW0-7

RDF/XML TURTLE JSON-LD última modificación 12/6/24

Loterre