Dependency or Span, End-to-End Uniform Semantic Role Labeling

Abstract

Semantic role labeling (SRL) aims to discover the predicateargument structure of a sentence. End-to-end SRL without syntactic input has received great attention. However, most of them focus on either span-based or dependency-based semantic representation form and only show specific model optimization respectively. Meanwhile, handling these two SRL tasks uniformly was less successful. This paper presents an end-to-end model for both dependency and span SRL with a unified argument representation to deal with two different types of argument annotations in a uniform fashion. Furthermore, we jointly predict all predicates and arguments, especially including long-term ignored predicate identification subtask. Our single model achieves new state-of-the-art results on both span (CoNLL 2005, 2012) and dependency (CoNLL 2008, 2009) SRL benchmarks.

References in corpus (2)

• Explicit Contextual Semantics for Text Comprehension
• Learning Joint Semantic Parsers from Disjoint Data

Cited by in corpus (8)

• Syntax-aware Multilingual Semantic Role Labeling
• Open-Domain Frame Semantic Parsing Using Transformers
• Effective Subword Segmentation for Text Comprehension
• Open Vocabulary Learning for Neural Chinese Pinyin IME
• Conversational Semantic Role Labeling
• Neural Unsupervised Semantic Role Labeling
• Semantic Role Labeling with Iterative Structure Refinement
• Capturing Argument Interaction in Semantic Role Labeling with Capsule Networks