Training Tree Transducers

Abstract

Many probabilistic models for natural language are now written in terms of hierarchical tree structure. Tree-based modeling still lacks many of the standard tools taken for granted in (finite-state) string-based modeling. The theory of tree transducer automata provides a possible framework to draw on, as it has been worked out in an extensive literature. We motivate the use of tree transducers for natural language and address the training problem for probabilistic tree-to-tree and tree-to-string transducers.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 2004
Accession Number
ADA460355

Entities

People

  • Jonathan Graehl
  • Kevin Knight

Organizations

  • University of Southern California

Tags

Communities of Interest

  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Algorithms
  • Artificial Intelligence
  • Automata Theory
  • Automated Speech Recognition
  • Computational Linguistics
  • Computational Science
  • Formal Languages
  • Grammars
  • Information Science
  • Language
  • Linguistics
  • Machine Translation
  • Markov Models
  • Natural Language Processing
  • Natural Languages
  • Probabilistic Models
  • Probability

Fields of Study

  • Computer science

Readers

  • Computational Linguistics
  • Software Engineering.