English

Classifying Long Clinical Documents with Pre-trained Transformers

Computation and Language 2021-05-17 v1

Abstract

Automatic phenotyping is a task of identifying cohorts of patients that match a predefined set of criteria. Phenotyping typically involves classifying long clinical documents that contain thousands of tokens. At the same time, recent state-of-art transformer-based pre-trained language models limit the input to a few hundred tokens (e.g. 512 tokens for BERT). We evaluate several strategies for incorporating pre-trained sentence encoders into document-level representations of clinical text, and find that hierarchical transformers without pre-training are competitive with task pre-trained models.

Keywords

Cite

@article{arxiv.2105.06752,
  title  = {Classifying Long Clinical Documents with Pre-trained Transformers},
  author = {Xin Su and Timothy Miller and Xiyu Ding and Majid Afshar and Dmitriy Dligach},
  journal= {arXiv preprint arXiv:2105.06752},
  year   = {2021}
}
R2 v1 2026-06-24T02:06:37.731Z