A Global Joint Model for Semantic Role Labeling

@article{Toutanova2008AGJ,
  title={A Global Joint Model for Semantic Role Labeling},
  author={Kristina Toutanova and Aria Haghighi and Christopher D. Manning},
  journal={Computational Linguistics},
  year={2008},
  volume={34},
  pages={161-191}
}
We present a model for semantic role labeling that effectively captures the linguistic intuition that a semantic argument frame is a joint structure, with strong dependencies among the arguments. We show how to incorporate these strong dependencies in a statistical joint model with a rich set of features over multiple argument phrases. The proposed model substantially outperforms a similar state-of-the-art local model that does not include dependencies among different arguments. We evaluate the… CONTINUE READING

Results and Topics from this paper.

Key Quantitative Results

  • The gains amount to 24.1% error reduction on all arguments and 36.8% on core arguments for gold-standard parse trees on Propbank.
  • This system achieves an error reduction of 24.1% on ALL arguments and 36.8% on CORE arguments over a state-of-the-art independent classifier for gold-standard parse trees on Propbank.

Citations

Publications citing this paper.
SHOWING 1-10 OF 117 CITATIONS

A Global Generative Model for Chinese Semantic Role Labeling

VIEW 5 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Unsupervised Semantic Role Induction with Global Role Ordering

VIEW 5 EXCERPTS
CITES METHODS, BACKGROUND & RESULTS
HIGHLY INFLUENCED

Syntactic Inductive Biases for Natural Language Processing

VIEW 4 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Computational linking theory

VIEW 4 EXCERPTS
CITES RESULTS & BACKGROUND
HIGHLY INFLUENCED

Open Question Answering

VIEW 5 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2007
2019

CITATION STATISTICS

  • 12 Highly Influenced Citations

References

Publications referenced by this paper.
SHOWING 1-10 OF 27 REFERENCES