Learning to Contextually Aggregate Multi-Source Supervision for Sequence Labeling

@article{Lan2020LearningTC,
  title={Learning to Contextually Aggregate Multi-Source Supervision for Sequence Labeling},
  author={Ouyu Lan and Xiao Huang and Bill Yuchen Lin and H. Jiang and Liyuan Liu and X. Ren},
  journal={ArXiv},
  year={2020},
  volume={abs/1910.04289}
}
  • Ouyu Lan, Xiao Huang, +3 authors X. Ren
  • Published 2020
  • Computer Science
  • ArXiv
  • Sequence labeling is a fundamental framework for various natural language processing problems. Its performance is largely influenced by the annotation quality and quantity in supervised learning scenarios, and obtaining ground truth labels is often costly. In many cases, ground truth labels do not exist, but noisy annotations or annotations from different domains are accessible. In this paper, we propose a novel framework Consensus Network (ConNet) that can be trained on annotations from… CONTINUE READING
    3 Citations

    Figures, Tables, and Topics from this paper

    LEAN-LIFE: A Label-Efficient Annotation Framework Towards Learning from Explanation
    • 3
    • PDF
    TriggerNER: Learning with Entity Triggers as Explanations for Named Entity Recognition
    • 8
    • PDF

    References

    SHOWING 1-10 OF 46 REFERENCES
    Low Resource Sequence Tagging with Weak Labels
    • 4
    • PDF
    LEAN-LIFE: A Label-Efficient Annotation Framework Towards Learning from Explanation
    • 3
    • PDF
    Heterogeneous Supervision for Relation Extraction: A Representation Learning Approach
    • 56
    • Highly Influential
    • PDF
    Sequence labeling with multiple annotators
    • 44
    • Highly Influential
    • PDF
    Semi-Supervised Sequence Modeling with Cross-View Training
    • 157
    • PDF
    Aggregating and Predicting Sequence Labels from Crowd Annotations
    • 38
    • Highly Influential
    • PDF
    Semi-Supervised Training Using Adversarial Multi-Task Learning for Spoken Language Understanding
    • Ouyu Lan, Su Zhu, K. Yu
    • Computer Science
    • 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
    • 2018
    • 10
    • PDF
    Learning From Crowds
    • 1,088
    • PDF
    Efficient Contextualized Representation: Language Model Pruning for Sequence Labeling
    • 27
    • PDF
    Deep learning from crowds
    • 55
    • PDF