The Physics of Text: Ontological Realism in Information Extraction

@inproceedings{Russell2016ThePO,
  title={The Physics of Text: Ontological Realism in Information Extraction},
  author={S. Russell and O. Lassen and J. Uang and W. Wang},
  booktitle={AKBC@NAACL-HLT},
  year={2016}
}
  • S. Russell, O. Lassen, +1 author W. Wang
  • Published in AKBC@NAACL-HLT 2016
  • Computer Science
  • We propose an approach to extracting information from text based on the hypothesis that text sometimes describes the world. The hypothesis is embodied in a generative probability model that describes (1) possible worlds and the facts they might contain, (2) how an author chooses facts to express, and (3) how those facts are expressed in text. Given text, information extraction is done by computing a posterior over the worlds that might have generated it. As a by-product, this unsupervised… CONTINUE READING
    1 Citations
    The Landscape of AI Safety and Beneficence Research: Input for Brainstorming at Beneficial AI 2017∗
    • Nmative Uertainty, Bunded Rionality, Cosistent Dcision
    • 2017
    • 5

    References

    SHOWING 1-10 OF 13 REFERENCES
    Joint inference of entities, relations, and coreference
    • 86
    • PDF
    Structured Relation Discovery using Generative Models
    • 128
    • Highly Influential
    • PDF
    Identity Uncertainty and Citation Matching
    • 343
    • PDF
    Reporting bias and knowledge acquisition
    • 74
    • PDF
    Extracting Patterns and Relations from the World Wide Web
    • 1,139
    • PDF
    A Bayesian Model of Plan Recognition
    • 489
    Never-Ending Learning
    • 523
    • PDF