Meta-Learning with Sparse Experience Replay for Lifelong Language Learning

By Nithin Holla, Pushkar Mishra, Helen Yannakoudakis, Ekaterina Shutova. 2020

25 citations recorded by the source corpus.

Lifelong learning requires models that can continuously learn from sequential streams of data without suffering catastrophic forgetting due to shifts in data distributions. Deep learning models have thrived in the non-sequential learning paradigm; however, when used to learn a sequence of tasks, they fail to retain past knowledge and learn incrementally. We propose a novel approach to lifelong learning of language tasks based on meta-learning with sparse experience replay that directly optimizes to prevent forgetting. We show that under the realistic setting of performing a single pass on a stream of tasks and without any task identifiers, our method obtains state-of-the-art results on lifelong text classification and relation extraction. We analyze the effectiveness of our approach and further demonstrate its low computational and space complexity.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Diyi Yang
2. Xuezhi Wang
3. Yanzhe Zhang
4. Jiaao Chen
5. Wei Zhou
6. Chengyu Wang
7. Jun Huang
8. Yuan Liu

In Computer Vision and Pattern Recognition

1. Wei Zhou
2. Diyi Yang
3. Yanzhe Zhang
4. Xuezhi Wang
5. Minghui Qiu
6. Yufan Huang
7. Jiaao Chen
8. Wei Lin

Citations in the corpus

• Continual Sequence Generation with Adaptive Compositional Modules (2022, background): “Comparing to continual learning on text classifi-cation and question answering (Wang et al., 2020; Holla et al., 2020; Huang et al., 2021), continual sequence generation is more challenging, since the output is no longer discrete labels but sequential text data in different styles/domains.”
• Continual Learning for Text Classification with Information Disentanglement Based Regularization (2021, background): “ing performance for text classification (de Masson d'Autume et al., 2019; Sun et al., 2019; Holla et al., 2020), relation extraction (Wang et al.”
• MeLL: Large-scale Extensible User Intent Classification for Dialogue Systems with Meta Lifelong Learning (2021, methodology): “Typical methods include experience replay [16, 20, 40], knowledge distillation [6, 26], transfer learning [5, 19, 39], etc.”
• Towards a robust experimental framework and benchmark for lifelong language learning (2021, unknown): “In the domain of language, a number of lifelong learning methods 123 have also been proposed, including embedding aligned episodic memory replay [38]; memory124 based parameter adaptation with sparse experience replay (MbPA++) [9]; meta-learning with sparse 125 experience replay [14]; and language m”