Model 1Model 2Model 3
ModelFine-tuned bert-base-uncasedFine-tuned bert-base-uncasedFine-tuned bert-base-uncased
Source embeddingConcatenate O*NET title and descriptionSeparate embeddings for O*NET title and O*NET title + descriptionSeparate embeddings for O*NET title and O*NET title + description
Target embeddingAverage pf concatenated permutations of ESCO (non-)preferred term(s)Separate embeddings for ESCO (non-)preferred term(s) and descriptionSeparate embeddings for ESCO (non-)preferred term(s) and description
ScoringCosine similarity (cs)0.4 * max(cs(ESCO pt/npts, O*NET title)) + 0.3 * median(cs(ESCO pt/npts, O*NET title)) + 0.3 * (cs(ESCO desc, O*NET title+desc))0.3 * max(cs(ESCO pt/npts, O*NET title)) + 0.15 * median(cs(ESCO pt/npts, O*NET title)) + 0.55 * (cs(ESCO desc, O*NET title+desc))
Batch size242424
Model updates2,395,2822,395,2822,826,735
Training size25,376,40025,376,40029,756,109