Year: 2020
Type: conference-paper
Abstract: While behaviors of pretrained language models (LMs) have been thoroughly examined, what happened during pretraining is rarely studied.We thus investigate the developmental process from a set of randomly initialized parameters to a totipotent 1 language model, which we refer to as the embryology of a pretrained language model.Our results show that ALBERT learns to reconstruct and predict tokens of different parts of speech (POS) in different learning speeds during pretraining.We also find that linguistic knowledge and world knowledge do not generally improve as pretraining proceeds, nor do downstream tasks' performance.These findings suggest that knowledge of a pretrained model varies during pretraining, and having more pretrain steps does not necessarily provide a model with more comprehensive knowledge.We provide source codes and pretrained models to reproduce our results at https://github. com/d223302/albert-embryology.
Authors: Cheng-Han Chiang, Sung-Feng Huang, Hung-yi Lee
Institution: National Taiwan University
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Funder: Delta Electronics
OpenAlex ID: W3092592453
