Skip to main content

Research Repository

Advanced Search

Clinical dialogue transcription error correction using Seq2Seq models.

Nanayakkara, Gayani; Wiratunga, Nirmalie; Corsar, David; Martin, Kyle; Wijekoon, Anjana

Authors



Abstract

Good communication is critical to good healthcare. Clinical dialogue is a conversation between health practitioners and their patients, with the explicit goal of obtaining and sharing medical information. This information contributes to medical decision-making regarding the patient and plays a crucial role in their healthcare journey. The reliance on note taking and manual scribing processes are extremely inefficient and leads to manual transcription errors when digitizing notes. Automatic Speech Recognition (ASR) plays a significant role in speech-to-text applications, and can be directly used as a text generator in conversational applications. However, recording clinical dialogue presents a number of general and domain-specific challenges. In this paper, we present a seq2seq learning approach for ASR transcription error correction of clinical dialogues. We introduce a new Gastrointestinal Clinical Dialogue (GCD) Dataset which was gathered by health-care professionals from a NHS Inflammatory Bowel Disease clinic and use this in a comparative study with four commercial ASR systems. Using self-supervision strategies, we fine-tune a seq2seq model on a mask-filling task using a domain-specific PubMed dataset which we have shared publicly for future research. The BART model fine-tuned for mask-filling was able to correct transcription errors and achieve lower word error rates for three out of four commercial ASR outputs .

Citation

NANAYAKKARA, G., WIRATUNGA, N., CORSAR, D., MARTIN, K. and WIJEKOON, A. 2022. Clinical dialogue transcription error correction using Seq2Seq models. arXiv [online]. Available from: https://doi.org/10.48550/arXiv.2205.13572

Deposit Date Oct 25, 2022
Publicly Available Date Oct 25, 2022
Keywords Clinical dialogue transcription; Automatic speech recognition; Error correction
Public URL https://rgu-repository.worktribe.com/output/1686647
Publisher URL https://doi.org/10.48550/arXiv.2205.13572
Related Public URLs https://rgu-repository.worktribe.com/output/1686809
Additional Information This is a preprint of an article that has been accepted for publication. Once published, the revised version will be available from the publisher's website: https://doi.org/10.1007/978-3-031-14771-5_4

Files





Related Outputs



You might also like



Downloadable Citations