Linguistic errors in the biomedical domain: Towards an error typology for Spanish

Abstract

The objective of this work is the analysis of errors contained in a corpus of medical reports in natural language and the design of a typology of errors, as there was no systematic review on verification and correction of errors in clinical documentation in Spanish. In the development of automatic detection and correction systems, it is of great interest to delve into the nature of the linguistic errors that occur in clinical reports, in order to detect and treat them properly. The results show that omission errors are the most frequent ones in the analyzed sample, and that word length certainly influences error frequency. The typification of error patterns provided is enabling the development of a module based on linguistic knowledge, which is currently in progress. This will help to improve the performance of error detection and correction systems for the biomedical domain.

Keywords

• automatic error detection
• candidate error
• error patterns
• biomedical corpus
• natural language processing.