Search Results for author:
Found 2 papers, 0 papers with code
DP-CRE: Continual Relation Extraction via Decoupled Contrastive Learning and Memory Structure Preservation
Continuous Relation Extraction (CRE) aims to incrementally learn relation knowledge from a non-stationary stream of data.
Handwritten Chinese Character Recognition by Convolutional Neural Network and Similarity Ranking
Experiments are done to compare the performances of a CNN model with three different loss functions.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
