Adapting BERT for Continual Learning of a Sequence of Aspect Sentiment Classification Tasks
Open paper
Benchmark
Model
Rank
Results
continual-learning-on-asc-19-tasks
B-CL
#3
F1 - macro: 0.8140
continual-learning-on-20newsgroup-10-tasks
B-CL
#4
F1 - macro: 0.9504
continual-learning-on-dsc-10-tasks
B-CL
#5
F1 - macro: 0.7651
Rank counts only results with a code link.