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

@inproceedings{He2017DeepSR,
  title={Deep Semantic Role Labeling: What Works and What's Next},
  author={Luheng He and Kenton Lee and Mike Lewis and Luke S. Zettlemoyer},
  booktitle={ACL},
  year={2017}
}
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… CONTINUE READING

Figures, Tables, Results, and Topics from this paper.

Key Quantitative Results

  • 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.
  • Our model gives a 10% relative error reduction over previous state of the art on the test sets of CoNLL 2005 and 2012.
  • We presented a new deep learning model for spanbased semantic role labeling with a 10% relative error reduction over the previous state of the art.

Similar Papers

Citations

Publications citing this paper.
SHOWING 1-10 OF 120 CITATIONS

Syntax-aware Neural Semantic Role Labeling

  • AAAI
  • 2019
VIEW 16 EXCERPTS
CITES METHODS, BACKGROUND & RESULTS
HIGHLY INFLUENCED

Large-Scale QA-SRL Parsing

VIEW 6 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Aware LSTM model for Semantic Role Labeling

VIEW 8 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Deep Semantic Role Labeling With Self-Attention

VIEW 16 EXCERPTS
CITES RESULTS, METHODS & BACKGROUND
HIGHLY INFLUENCED

Domain Adaptation of SRL Systems for Biological Processes

  • BioNLP@ACL
  • 2019
VIEW 7 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

TRANSFER LEARNING IN NATURAL LANGUAGE PRO-

VIEW 7 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2016
2019

CITATION STATISTICS

  • 36 Highly Influenced Citations

  • Averaged 40 Citations per year from 2017 through 2019

References

Publications referenced by this paper.
SHOWING 1-10 OF 34 REFERENCES

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

Xavier Carreras, Lluı́s Màrquez
  • In Proceedings of the Ninth Conference on Computational Natural Language Learning. Association for Computational Linguistics,
  • 2005
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

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

Xavier Carreras, Lluı́s Màrquez
  • In Proceedings of the Ninth Conference on Computational Natural Language Learning. Association for Computational Linguistics,
  • 2005
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

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

Xavier Carreras, Lluı́s Màrquez
  • In Proceedings of the Ninth Conference on Computational Natural Language Learning. Association for Computational Linguistics,
  • 2005
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Efficient Inference and Structured Learning for Semantic Role Labeling

  • Transactions of the Association for Computational Linguistics
  • 2015
VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

ADADELTA: An Adaptive Learning Rate Method

VIEW 2 EXCERPTS
HIGHLY INFLUENTIAL