ALBERT: A Lite BERT for Self-supervised Learning of Language Representations

Zhenzhong Lan, Mingda Chen, Sebastian Goodman et al.

2019 · arXiv (Cornell University) · 984 citations

Increasing model size when pretraining natural language representations often results in improved performance on downstream tasks. However, at some point further model increases become harder due to GPU/TPU memory limitations and longer training times. To address these problems, we present two parameter-reduction techniques to lower memory consumption and increase the training speed of BERT. Comprehensive empirical evidence shows that our proposed methods lead to models that scale much better compared to the original BERT. We also use a self-supervised loss that focuses on modeling inter-sent…

Read the paper →

Explore this paper's citation graph on Constellation.