Structure and Performance of a Dependency Language Model

Abstract

We present a maximum entropy language model that incorporates both syntax and semantics via a dependency grammar. Such a grammar expresses the relations between words by a directed graph. Because the edges of this graph may connect words that are arbitrarily far apart in a sentence, this technique can incorporate the predictive power of words that lie outside of bigram or trigram range. we have built several simple dependency models, as we call them, and tested them in a speech recognition experiment. We report experimental results for these models here, including one that has a small but statistically significant advantage (p < .02) over a digram language model.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Sep 01, 1997
Accession Number
ADA640606

Entities

People

  • Andreas Stolcke
  • Ciprian Chelba
  • David Engle
  • Dekai Wu
  • Eric Ristad
  • Frederick Jelinek
  • Harry Printz
  • Lidia Mangue
  • Roni Rosenfeld
  • Sanjeev Khudanpur
  • Victor Jimenez

Organizations

  • SRI International

Tags

Communities of Interest

  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Automated Speech Recognition
  • Computational Linguistics
  • Computer Science
  • Decomposition
  • Grammars
  • Language
  • Linguistics
  • Models
  • Natural Languages
  • Probabilistic Models
  • Probability
  • Probability Distributions
  • Semantics
  • Sequences
  • Training
  • Words (Language)

Fields of Study

  • Computer science

Readers

  • Computational Linguistics
  • Computational Modeling and Simulation
  • Graph Algorithms and Convex Optimization.

Technology Areas

  • AI & ML
  • AI & ML - Machine Learning Algorithms
  • AI & ML - Machine Translation