Skip to main content
. 2020 Jun 3;117(48):30046–30054. doi: 10.1073/pnas.1907367117

Table 1.

Well-performing BERT attention heads on WSJ SD dependency parsing by dependency type

Attention Baseline
Relation precision precision
Microaverage across
  dependency types
 Best single head 34.5 26.3
 Best head per dependency type 69.3 50.8
Single heads for individual
  dependency types
 Nominal subject 58.4 45.4
 Direct object 86.8 40.0
 Clausal complement 48.8 12.4
 Object of preposition 76.3 34.6
 Predeterminer 94.3 51.7
 Marker 50.7 14.5
 Passive auxiliary 82.5 40.5
 Phrasal verb particle 99.1 91.4