Papers with catastrophically forgetting

2 papers
Continual Learning Long Short Term Memory (2020.findings-emnlp)

Copied to clipboard

Challenge: Existing approaches to prevent catastrophic forgetting in neural networks are based on the stability-plasticity dilemma, but only a limited size of old data is available.
Approach: They propose a Continual Learning Long Short Term Memory cell in Recurrent Neural Network (RNN) that considers the state of each individual task's output gates and the correlation of the states between tasks.
Outcome: The proposed method significantly improves on spoken language understanding tasks over state-of-the-art approaches.
Continual Machine Reading Comprehension via Uncertainty-aware Fixed Memory and Adversarial Domain Adaptation (2022.findings-naacl)

Copied to clipboard

Challenge: Existing stationary-trained MRC systems are usually trained with in-domain data but are applied to new domain data.
Approach: They propose a continual machine reading comprehension model with uncertainty-aware fixed memory and adversarial domain adaptation that keeps a stable understanding by learning both memory and new domain data.
Outcome: The proposed model is superior to strong baselines and has a substantial incremental learning ability without catastrophically forgetting under two different continual MRC settings.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations