Episodic Memory in Lifelong Language Learning

Abstract

We introduce a lifelong language learning setup where a model needs to learn from a stream of text examples without any dataset identifier. We propose an episodic memory model that performs sparse experience replay and local adaptation to mitigate catastrophic forgetting in this setup. Experiments on text classification and question answering demonstrate the complementary benefits of sparse experience replay and local adaptation to allow the model to continuously learn from new datasets. We also show that the space complexity of the episodic memory module can be reduced significantly (~50-90%) by randomly choosing which examples to store in memory with a minimal decrease in performance. We consider an episodic memory component as a crucial building block of general linguistic intelligence and see our model as a first step in that direction.

arXiv commentProceedings of NeurIPS 2019

Cited by in corpus (7)

• Inherit with Distillation and Evolve with Contrast: Exploring Class Incremental Semantic Segmentation Without Exemplar Memory
• Localising In-Domain Adaptation of Transformer-Based Biomedical Language Models
• Continuous learning of spiking networks trained with local rules
• DRILL: Dynamic Representations for Imbalanced Lifelong Learning
• Curriculum-Meta Learning for Order-Robust Continual Relation Extraction
• Continual Machine Reading Comprehension via Uncertainty-aware Fixed Memory and Adversarial Domain Adaptation
• Graceful Forgetting II. Data as a Process