From News to Medical: Cross-domain Discourse Segmentation
This work addresses discourse segmentation for medical texts, but it is incremental as it primarily analyzes cross-domain performance without introducing new methods.
The study tackled the problem of discourse segmentation in the medical domain by annotating a small-scale corpus and evaluating news-trained segmenters, finding a performance drop and identifying error types that suggest both pipeline adjustments and corpus expansion are needed for improvement.
The first step in discourse analysis involves dividing a text into segments. We annotate the first high-quality small-scale medical corpus in English with discourse segments and analyze how well news-trained segmenters perform on this domain. While we expectedly find a drop in performance, the nature of the segmentation errors suggests some problems can be addressed earlier in the pipeline, while others would require expanding the corpus to a trainable size to learn the nuances of the medical domain.