Year: 2023
Type: conference-paper
Abstract: Transformer-based masked language models such as BERT, trained on general corpora, have shown impressive performance on downstream tasks.It has also been demonstrated that the downstream task performance of such models can be improved by pretraining larger models for longer on more data.In this work, we empirically evaluate the extent to which these results extend to tasks in science.We use 14 domain-specific transformer-based models (including SCHOLARBERT, a new 770Mparameter science-focused masked language model pretrained on up to 225B tokens) to evaluate the impact of training data, model size, pretraining and finetuning time on 12 downstream scientific tasks.Interestingly, we find that increasing model size, training data, or compute time does not always lead to significant improvements (i.e., > 1% F1), if any, in scientific information extraction tasks.We offer possible explanations for this surprising result.
Authors: Zhi Hong, Aswathy Ajith, James Pauloski, Eamon Duede, Kyle Chard, Ian Foster
Institutions: University of Chicago, Argonne National Laboratory
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W4385572478