English

Factuality Detection using Machine Translation -- a Use Case for German Clinical Text

Computation and Language 2023-08-21 v1

Abstract

Factuality can play an important role when automatically processing clinical text, as it makes a difference if particular symptoms are explicitly not present, possibly present, not mentioned, or affirmed. In most cases, a sufficient number of examples is necessary to handle such phenomena in a supervised machine learning setting. However, as clinical text might contain sensitive information, data cannot be easily shared. In the context of factuality detection, this work presents a simple solution using machine translation to translate English data to German to train a transformer-based factuality detection model.

Keywords

Cite

@article{arxiv.2308.08827,
  title  = {Factuality Detection using Machine Translation -- a Use Case for German Clinical Text},
  author = {Mohammed Bin Sumait and Aleksandra Gabryszak and Leonhard Hennig and Roland Roller},
  journal= {arXiv preprint arXiv:2308.08827},
  year   = {2023}
}

Comments

Accepted at KONVENS 2023

R2 v1 2026-06-28T11:57:44.203Z