Jointly Predicting Predicates and Arguments in Neural Semantic Role Labeling

ACL 2018 Luheng HeKenton LeeOmer LevyLuke Zettlemoyer

Recent BIO-tagging-based neural semantic role labeling models are very high performing, but assume gold predicates as part of the input and cannot incorporate span-level features. We propose an end-to-end approach for jointly predicting all predicates, arguments spans, and the relations between them... (read more)

PDF Abstract

Evaluation Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK COMPARE
Semantic Role Labeling (predicted predicates) CoNLL 2005 He et al. 2018 F1 82.5 # 4
Semantic Role Labeling (predicted predicates) CoNLL 2005 He et al. 2018 + ELMo F1 86.0 # 2
Semantic Role Labeling (predicted predicates) CoNLL 2012 He et al. 2018 F1 79.8 # 4
Semantic Role Labeling (predicted predicates) CoNLL 2012 He et al. 2018 + ELMo F1 82.9 # 2
Semantic Role Labeling OntoNotes He et al., F1 85.5 # 4
Semantic Role Labeling OntoNotes He et al. F1 82.1 # 7