Annotating the Focus of Negation in Terms of Questions Under Discussion

Abstract

Blanco & Moldovan have empirically demonstrated that negated sentences often convey implicit positive inferences, or focus, and that these inferences are both human annotatable and machine learnable. Concentrating on their annotation process, this paper argues that the focus-based implicit positivity should be separated from concepts of scalar implicature and neg-raising as well as the placement of stress. We show that a model making these distinctions clear and which incorporates the pragmatic notion of question under discussion yields kappa rates above .80, but that it substantially deflates the rates of focus of negation in text.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jul 13, 2012
Accession Number
ADA590555

Entities

People

  • Craig Martell
  • Pranav Anand

Organizations

  • Naval Postgraduate School

Tags

Communities of Interest

  • Autonomy

DTIC Thesaurus Topics

  • Abstracts
  • California
  • Computational Linguistics
  • Computer Science
  • Contracts
  • Grammars
  • Hot Water
  • Information Operations
  • Language
  • Linguistics
  • Machine Learning
  • Natural Languages
  • Standards
  • Universities
  • Water

Readers

  • Computational Linguistics
  • Linear Algebra
  • Neural Network Machine Learning.

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - Information Retrieval
  • AI & ML - Neural Networks