transformer-srl 2.0.dev20202807

SRL Transformer model

Semantic Role Lableing with BERT

Semantic Role Labeling based on AllenNLP implementation of Shi et al, 2019. It uses VerbAatlas inventory and it's trained also on predicate disambiguation, in addition to arguments identification and disambiguation.

• Language Model: BERT
• Dataset: CoNLL 2012

Results

With bert-base-cased:

# Dev set
- F1 arguments 87.6
- F1 predicates 95.5
# Test set
- F1 arguments x
- F1 predicates x

With bert-base-multilingual-cased:

# Dev set
- F1 arguments 86.2
- F1 predicates 94.2
# Test set
- F1 arguments 86.1
- F1 predicates 94.9