Skip to main content

Table 6 Full end-to-end system evaluation on the core + extensions set comparing F1 score for the top two algorithms found in the core set

From: Concept recognition as a machine translation problem

Ontology

CRF

BioBERT

UZH@CRAFT-ST

ChEBI_EXT

0.7891

0.8039

0.8209*

CL_EXT

0.7381

0.7491*

0.7484

GO_BP_EXT

0.7279

0.7353

0.8138*

GO_CC_EXT

0.8738

0.8983*

0.8936

GO_MF_EXT

0.6413

0.6255

0.7438*

MOP_EXT

0.8000

0.8651*

0.8437

NCBITaxon_EXT

0.8710

0.8624

0.9722*

PR_EXT

0.4397

0.5188

0.8011*

SO_EXT

0.7682

0.7829

0.9187*

UBERON_EXT

0.7558

0.7711

0.7714*

  1. For all results shown here, the span detection algorithm is listed, and the concept normalization algorithm is OpenNMT. UZH@CRAFT-ST is the best performing system from Furrer et al. [4] in the CRAFT-ST, shown as a comparison to our methods. The best-performing algorithm is bolded with an asterisk*
Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us