Learning Joint Semantic Parsers from Disjoint Data

@inproceedings{Peng2018LearningJS,
  title={Learning Joint Semantic Parsers from Disjoint Data},
  author={Hao Peng and Sam Thomson and Swabha Swayamdipta and Noah A. Smith},
  booktitle={NAACL-HLT},
  year={2018}
}
  • Hao Peng, Sam Thomson, +1 author Noah A. Smith
  • Published in NAACL-HLT 2018
  • Computer Science
  • We present a new approach to learning semantic parsers from multiple datasets, even when the target semantic formalisms are drastically different, and the underlying corpora do not overlap. We handle such "disjoint" data by treating annotations for unobserved formalisms as latent structured variables. Building on state-of-the-art baselines, we show improvements both in frame-semantic parsing and semantic dependency parsing by modeling them jointly. 
    39 Citations
    Compositional Semantic Parsing Across Graphbanks
    • 24
    • PDF
    Syntactic Scaffolds for Semantic Structures
    • 57
    • PDF
    Mutlitask Learning for Cross-Lingual Transfer of Semantic Dependencies
    • PDF
    Open-Domain Frame Semantic Parsing Using Transformers
    • 2
    • PDF
    Multitask Parsing Across Semantic Representations
    • 53
    • Highly Influenced
    • PDF
    Broad-Coverage Semantic Parsing as Transduction
    • 26
    • PDF
    Encoding Syntactic Constituency Paths for Frame-Semantic Parsing with Graph Convolutional Networks
    • Highly Influenced
    • PDF

    References

    SHOWING 1-10 OF 59 REFERENCES
    Deep Multitask Learning for Semantic Dependency Parsing
    • 110
    • PDF
    Frame-Semantic Role Labeling with Heterogeneous Annotations
    • 61
    • PDF
    Using Semantic Roles to Improve Question Answering
    • 392
    • PDF
    The CoNLL 2008 Shared Task on Joint Parsing of Syntactic and Semantic Dependencies
    • 490
    • Highly Influential
    • PDF
    Semantic Role Labeling with Neural Network Factors
    • 115
    • Highly Influential
    • PDF
    Probabilistic Frame-Semantic Parsing
    • 179
    • PDF
    A Joint Sequential and Relational Model for Frame-Semantic Parsing
    • 40
    • Highly Influential
    • PDF
    Automatic Labeling of Semantic Roles
    • 930
    • PDF
    Improving NLP through Marginalization of Hidden Syntactic Structure
    • 31
    • PDF