Towards Semi-Supervised Learning for Deep Semantic Role Labeling

@inproceedings{Mehta2018TowardsSL,
  title={Towards Semi-Supervised Learning for Deep Semantic Role Labeling},
  author={Sanket Vaibhav Mehta and Jay Yoon Lee and J. Carbonell},
  booktitle={EMNLP},
  year={2018}
}
  • Sanket Vaibhav Mehta, Jay Yoon Lee, J. Carbonell
  • Published in EMNLP 2018
  • Computer Science
  • Neural models have shown several state-of-the-art performances on Semantic Role Labeling (SRL). However, the neural models require an immense amount of semantic-role corpora and are thus not well suited for low-resource languages or domains. The paper proposes a semi-supervised semantic role labeling method that outperforms the state-of-the-art in limited SRL training corpora. The method is based on explicitly enforcing syntactic constraints by augmenting the training objective with a syntactic… CONTINUE READING
    10 Citations
    Semi-Supervised Semantic Role Labeling with Cross-View Training
    • 7
    • PDF
    Structured Tuning for Semantic Role Labeling
    • 1
    • PDF
    Injecting constraints into neural NLP models
    A Primal Dual Formulation For Deep Learning With Constraints
    • 6
    • Highly Influenced
    • PDF
    Augmenting Neural Networks with First-order Logic
    • 21
    • PDF
    A Logic-Driven Framework for Consistency of Neural Models
    • 9
    • PDF
    A Simple and Effective Model for Answering Multi-span Questions
    • 4
    • PDF

    References

    SHOWING 1-10 OF 16 REFERENCES
    Semi-supervised Semantic Role Labeling Using the Latent Words Language Model
    • 81
    • PDF
    End-to-end learning of semantic role labeling using recurrent neural networks
    • Jie Zhou, W. Xu
    • Computer Science
    • ACL
    • 2015
    • 260
    • PDF
    Deep Semantic Role Labeling: What Works and What's Next
    • 278
    • Highly Influential
    • PDF
    Towards Open-Domain Semantic Role Labeling
    • 29
    • Highly Influential
    • PDF
    The Importance of Syntactic Parsing and Inference in Semantic Role Labeling
    • 391
    • PDF
    Towards Robust Linguistic Analysis using OntoNotes
    • 170
    • PDF
    Gradient-Based Inference for Networks with Output Constraints
    • 16
    • PDF
    Deep contextualized word representations
    • 4,595
    • Highly Influential
    • PDF
    Generalized Inference with Multiple Semantic Role Labeling Systems
    • 148
    • PDF
    Using Semantic Roles to Improve Question Answering
    • 384
    • PDF