Title
Evaluation of pooling operations in convolutional architectures for drug-drug interaction extraction.
Abstract
Max-pooling outperforms the others alternatives because is the only one which is invariant to the special pad tokens that are appending to the shorter sentences known as padding. Actually, the combination of max-pooling and attentive pooling does not improve the performance as compared with the single max-pooling technique.
Year
DOI
Venue
2018
10.1186/s12859-018-2195-1
BMC Bioinformatics
Keywords
Field
DocType
Attention model,Convolutional neural network,Deep learning,Drug-drug interaction extraction,Pooling
Drug-drug interaction,Pattern recognition,Biology,Convolution,Convolutional neural network,Pooling,Curse of dimensionality,Invariant (mathematics),Artificial intelligence,Deep learning,Bioinformatics,Padding
Journal
Volume
Issue
ISSN
19-S
8
1471-2105
Citations 
PageRank 
References 
1
0.43
17
Authors
2
Name
Order
Citations
PageRank
Víctor Suárez-Paniagua141.84
Isabel Segura-Bedmar243530.96