Skip to main content

Table 5 Performance of the deep joint learning method on each type of FM information and relation

From: Family history information extraction via deep joint learning

 TypePRF
FM information recognitionFM (Maternal)0.94120.95520.9481
FM (Paternal)0.92860.78000.8478
FM (NA)0.84520.88750.8659
Observation0.87530.91460.8945
LSa0.84180.91160.8753
Overall0.87750.90300.8901
Relation ExtractionFM-LS0.60840.62730.6177
FM- Observation0.64510.64510.6451
Overall0.63270.63920.6359
  1. aThe results are obtained according to the gold LS mentions, not the gold standard LSs for final evaluation, which are not provided. Therefore, the overall performance on FM information recognition does not cover LS