A Case Study on Pros and Cons of Regular Expression Detection and Dependency Parsing for Negation Extraction from German Medical Documents. Technical Report
This work addresses information extraction challenges for medical professionals handling German documents, but it is incremental as it builds on existing methods like NegEx and Stanford CoreNLP.
The researchers compared regular expression detection and dependency parsing for extracting negations from German medical documents, finding that a significantly smaller trigger set could achieve similar results to reduce adaptation time to new text types.
We describe our work on information extraction in medical documents written in German, especially detecting negations using an architecture based on the UIMA pipeline. Based on our previous work on software modules to cover medical concepts like diagnoses, examinations, etc. we employ a version of the NegEx regular expression algorithm with a large set of triggers as a baseline. We show how a significantly smaller trigger set is sufficient to achieve similar results, in order to reduce adaptation times to new text types. We elaborate on the question whether dependency parsing (based on the Stanford CoreNLP model) is a good alternative and describe the potentials and shortcomings of both approaches.