High-order Semantic Role Labeling
Zuchao Li, Hai Zhao, Rui Wang, Kevin Parnow · 2020
Semantic role labeling is primarily used to identify predicates, arguments, and their semantic relationships.Due to the limitations of modeling methods and the conditions of pre-identified predicates, previous work has focused on the relationships between predicates and arguments and the correlations between arguments at most, while the correlations between predicates have been neglected for a long time.High-order features and structure learning were very common in modeling such correlations before the neural network era.In this paper, we introduce a highorder graph structure for the neural semantic role labeling model, which enables the model to explicitly consider not only the isolated predicate-argument pairs but also the interaction between the predicate-argument pairs.Experimental results on 7 languages of the CoNLL-2009 benchmark show that the highorder structural learning techniques are beneficial to the strong performing SRL models and further boost our baseline to achieve new stateof-the-art results.