Information Extraction from Swedish Medical Prescriptions with Sig-Transformer Encoder

TL;DR

This paper introduces a novel Sig-Transformer encoder that enhances clinical NLP tasks on Swedish prescriptions by integrating signature transforms into the Transformer architecture, outperforming baseline models in key information extraction tasks.

Contribution

The work presents a new Transformer extension with signature transforms, improving Swedish medical prescription information extraction over existing models.

Findings

Superior performance in two of three tasks compared to baselines

Signature transform integration enhances model capabilities

Evaluation of multilingual BERT versus translated text encoding

Abstract

Relying on large pretrained language models such as Bidirectional Encoder Representations from Transformers (BERT) for encoding and adding a simple prediction layer has led to impressive performance in many clinical natural language processing (NLP) tasks. In this work, we present a novel extension to the Transformer architecture, by incorporating signature transform with the self-attention model. This architecture is added between embedding and prediction layers. Experiments on a new Swedish prescription data show the proposed architecture to be superior in two of the three information extraction tasks, comparing to baseline models. Finally, we evaluate two different embedding approaches between applying Multilingual BERT and translating the Swedish text to English then encode with a BERT model pretrained on clinical notes.