SciBERT: A Pretrained Language Model for Scientific Text
TL
TL;DR
SciBERT leverages unsupervised pretraining on a large multi-domain corpus of scientific publications to improve performance on downstream scientific NLP tasks and demonstrates statistically significant improvements over BERT.
Abstract
Obtaining large-scale annotated data for NLP tasks in the scientific domain is challenging and expensive. We release SciBERT, a pretrained language model based on BERT (Devlin et. al., 2018) to address the lack of high-quality, large-scale labeled scientific data. SciBERT leverages unsupervised pretraining on a large multi-domain corpus of scientific publications to improve performance on downstream scientific NLP tasks. We evaluate on a suite of tasks including sequence tagging, sentence classification and dependency parsing, with datasets from a variety of scientific domains. We demonstrate statistically significant improvements over BERT and achieve new state-of-the-art results on several of these tasks. The code and pretrained models are available at https://github.com/allenai/scibert/.
References32 items
1
ClinicalBERT: Modeling Clinical Notes and Predicting Hospital Readmission
2
Publicly Available Clinical BERT Embeddings
3
Structural Scaffolds for Citation Intent Classification in Scientific Publications
4
ScispaCy: Fast and Robust Models for Biomedical Natural Language Processing
5