Can I read Self-supervised Answer Retrieval on Clinical Notes on EtoBox?

Self-supervised Answer Retrieval on Clinical Notes by Grundmann, Paul; Arnold, Sebastian; Löser, Alexander is a scholarly article available to read on EtoBox.

What is Self-supervised Answer Retrieval on Clinical Notes about?

Retrieving answer passages from long documents is a complex task requiring semantic understanding of both discourse and document context. We approach this challenge specifically in a clinical scenario, where doctors retrieve cohorts of patients based on diagnoses and other latent medical aspects. We introduce CAPR, a rule-based self-supervision objective for training Transformer language models for domain-specific passage matching. In addition, we contribute a novel retrieval dataset based on clinical notes to simulate this scenario on a large corpus of clinical notes. We apply our objective in four Transformer-based architectures: Contextual Document Vectors, Bi-, Poly- and Cross-encoders. From our extensive evaluation on MIMIC-III and three other healthcare datasets, we report that CAPR outperforms strong baselines in the retrieval of domain-specific passages and effectively generalizes across rule-based and human-labeled passages. This makes the model powerful especially in zero-shot scenarios where only limited training data is available.

Author

Grundmann, Paul; Arnold, Sebastian; Löser, Alexander

Published

2021

Language

EN