On the Limits of Learning to Actively Learn Semantic Representations

@article{Koshorek2019OnTL,
  title={On the Limits of Learning to Actively Learn Semantic Representations},
  author={Omri Koshorek and Gabriel Stanovsky and Yi-chu Zhou and Vivek Srikumar and Jonathan Berant},
  journal={ArXiv},
  year={2019},
  volume={abs/1910.02228}
}
One of the goals of natural language understanding is to develop models that map sentences into meaning representations. However, training such models requires expensive annotation of complex structures, which hinders their adoption. Learning to actively-learn (LTAL) is a recent paradigm for reducing the amount of labeled data by learning a policy that selects which samples should be labeled. In this work, we examine LTAL for learning semantic representations, such as QA-SRL. We show that even… Expand
4 Citations
Uncertainty and Traffic-Aware Active Learning for Semantic Parsing
  • PDF
Dialog as a Vehicle for Lifelong Learning
  • PDF

References

SHOWING 1-10 OF 36 REFERENCES
Reducing Labeling Effort for Structured Prediction Tasks
  • 257
  • PDF
Multitask Parsing Across Semantic Representations
  • 54
  • PDF
Practical Obstacles to Deploying Active Learning
  • 25
  • PDF
Learning how to Active Learn: A Deep Reinforcement Learning Approach
  • 115
  • PDF
Question-Answer Driven Semantic Role Labeling: Using Natural Language to Annotate Natural Language
  • 113
  • Highly Influential
  • PDF
AllenNLP: A Deep Semantic Natural Language Processing Platform
  • 602
  • Highly Influential
  • PDF
Active Learning Literature Survey
  • 3,832
  • PDF
Human-in-the-Loop Parsing
  • 20
  • PDF
The Proposition Bank: An Annotated Corpus of Semantic Roles
  • 2,269
  • PDF
...
1
2
3
4
...