Papers › Continual BERT: Continual Learning for Adaptive Extractive Summarization of COVID-19 Literature

Continual BERT: Continual Learning for Adaptive Extractive Summarization of COVID-19 Literature

7 Jul 2020arXiv:2007.03405archive 2025-07-28

Jong Won Park

The scientific community continues to publish an overwhelming amount of new research related to COVID-19 on a daily basis, leading to much literature without little to no attention. To aid the community in understanding the rapidly flowing array of COVID-19 literature, we propose a novel BERT architecture that provides a brief yet original summarization of lengthy papers. The model continually learns on new data in online fashion while minimizing catastrophic forgetting, thus fitting to the need of the community. Benchmark and manual examination of its performance show that the model provide a sound summary of new scientific literature.

PaperPDFCode

Code

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Continual LearningExtractive Summarization

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AdamAttentionAttention DropoutBERTDense ConnectionsDropoutLayer NormalizationLinear LayerLinear Warmup With Linear DecayMulti-Head AttentionResidual ConnectionSoftmaxWeight DecayWordPiece

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections