Iterative Refinement and Quality Checking of Annotation Guidelines - How to Deal Effectively with Semantically Sloppy Named Entity Types, such as Pathological Phenomena.

We here discuss a methodology for dealing with the annotation of semantically hard to delineate, i.e., sloppy, named entity types. To illustrate sloppiness of entities, we treat an example from the medical domain, namely pathological phenomena. Based on our experience with iterative guideline refinement we propose to carefully characterize the thematic scope of the annotation by positive and negative coding lists and allow for alternative, short vs. long mention span annotations. Short spans account for canonical entity mentions (e.g., standardized disease names), while long spans cover descriptive text snippets which contain entity-specific elaborations (e.g., anatomical locations, observational details, etc.). Using this stratified approach, evidence for increasing annotation performance is provided by kappa-based inter-annotator agreement measurements over several, iterative annotation rounds using continuously refined guidelines. The latter reflects the increasing understanding of the sloppy entity class both from the perspective of guideline writers and users (annotators). Given our data, we have gathered evidence that we can deal with sloppiness in a controlled manner and expect inter-annotator agreement values around 80% for PATHOJEN, the pathological phenomena corpus currently under development in our lab.