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

Abstract

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. Our 8-layer ensemble model achieves 83.2 F1 on the CoNLL 2005 test set and 83.4 F1 on CoNLL 2012, roughly a 10% relative error reduction over the previous state of the art. Extensive empirical analysis of these gains show that (1) deep models excel at recovering long-distance dependencies but can still make surprisingly obvious errors, and (2) that there is still room for syntactic parsers to improve these results.

DOI: 10.18653/v1/P17-1044
Showing 1-10 of 30 references

Introduction to the conll-2005 shared task: Semantic role labeling

  • Xavier Carreras, Lluı́s Màrquez
  • 2005
Highly Influential
4 Excerpts