Greedy, Joint Syntactic-Semantic Parsing with Stack LSTMs

@article{Swayamdipta2016GreedyJS,
  title={Greedy, Joint Syntactic-Semantic Parsing with Stack LSTMs},
  author={Swabha Swayamdipta and Miguel Ballesteros and Chris Dyer and Noah A. Smith},
  journal={ArXiv},
  year={2016},
  volume={abs/1606.08954}
}
We present a transition-based parser that jointly produces syntactic and semantic dependencies. It learns a representation of the entire algorithm state, using stack long short-term memories. Our greedy inference algorithm has linear time, including feature extraction. On the CoNLL 2008--9 English shared tasks, we obtain the best published parsing performance among models that jointly learn syntax and semantics. 
57 Citations
Deep Multitask Learning for Semantic Dependency Parsing
  • 114
  • PDF
Frame-Semantic Parsing with Softmax-Margin Segmental RNNs and a Syntactic Scaffold
  • 62
  • PDF
Multiple Tasks Integration: Tagging, Syntactic and Semantic Parsing as a Single Task
  • PDF
Semantic Role Labeling as Syntactic Dependency Parsing
  • PDF
Syntactic Scaffolds for Semantic Structures
  • 59
  • PDF
A Joint Sequential and Relational Model for Frame-Semantic Parsing
  • 41
  • PDF
Joint Bi-Affine Parsing and Semantic Role Labeling
  • 1
  • Highly Influenced
  • PDF
AMR Parsing using Stack-LSTMs
  • 41
  • PDF
IBM Research at the CoNLL 2018 Shared Task on Multilingual Parsing
  • 4
  • PDF
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 59 REFERENCES
Multilingual Dependency-based Syntactic and Semantic Parsing
  • 66
  • PDF
A Latent Variable Model of Synchronous Parsing for Syntactic and Semantic Dependencies
  • 62
  • Highly Influential
  • PDF
Joint Arc-factored Parsing of Syntactic and Semantic Dependencies
  • 36
  • PDF
A Joint Model for Parsing Syntactic and Semantic Dependencies
  • 24
  • PDF
Joint Parsing and Semantic Role Labeling
  • 65
  • PDF
A Cascaded Syntactic and Semantic Dependency Parsing System
  • 41
  • PDF
Improved Transition-based Parsing by Modeling Characters instead of Words with LSTMs
  • 273
  • PDF
...
1
2
3
4
5
...