Episodic Memory in Lifelong Language Learning

TL;DR

This paper presents a lifelong language learning framework using episodic memory to enable models to learn continuously from text streams, effectively mitigating catastrophic forgetting and reducing memory requirements.

Contribution

It introduces an episodic memory model with sparse experience replay and local adaptation for lifelong language learning, demonstrating its effectiveness on text classification and question answering tasks.

Findings

Sparse experience replay improves continual learning performance.

Local adaptation enhances model flexibility in new datasets.

Memory space can be reduced by 50-90% with minimal performance loss.

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.