Use of Modality and Negation in Semantically-Informed Syntactic MT

Abstract

Hopkins Human Language Technology Center of Excellence Summer Camp for Applied Language Exploration (SCALE-2009) on Semantically Informed Machine Translation (SIMT) (Baker et al. 2010a, 2010b, 2010c, 2010d). Specifically, we describe our modality/ negation (MN) annotation scheme, a (publicly available) MN lexicon, and two automated MNtaggers that were built using the lexicon and annotation scheme. Our annotation scheme isolates three components of modality and negation: a trigger (a word that conveys modality or negation), a target (an action associated with modality or negation), and a holder (an experiencer of modality). Two examples of MN tagging are shown in Figure 1.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jun 01, 2012
Accession Number
ADA563998

Entities

People

  • Bonnie J. Dorr
  • Chris Callison-burch
  • Christine Piatko
  • Kathryn Baker
  • Lori Levin
  • Michael Bloodgood
  • Nathaniel W. Filardo
  • Scott R. Miller

Organizations

  • United States Department of Defense

Tags

Communities of Interest

  • Biomedical

DTIC Thesaurus Topics

  • Artificial Intelligence
  • Artificial Intelligence Software
  • Computational Linguistics
  • Computational Science
  • Electronic Mail
  • Grammars
  • Hidden Markov Models
  • Language
  • Linguistics
  • Machine Learning
  • Machine Translation
  • Markov Models
  • Natural Language Processing
  • Natural Languages
  • Nuclear Bombs
  • Supervised Machine Learning
  • Test Sets

Readers

  • Computational Linguistics
  • Medical Imaging.

Technology Areas

  • AI & ML
  • AI & ML - Machine Translation