Deep Semantic Role Labeling: What Works and What's Next

ACL 2017 Luheng HeKenton LeeMike LewisLuke Zettlemoyer

We introduce a new deep learning model for semantic role labeling (SRL) that significantly improves the state of the art, along with detailed analyses to reveal its strengths and limitations. We use a deep highway BiLSTM architecture with constrained decoding, while observing a number of recent best practices for initialization and regularization... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK LEADERBOARD
Predicate Detection CoNLL 2005 DeepSRL F1 96.4 # 2
Semantic Role Labeling OntoNotes He et al. F1 81.7 # 8