Automatically Acquiring Phrase Structure Using Distributional Analysis

Abstract

In this paper, we present evidence that the acquisition of the phrase structure of a natural language is possible without supervision and with a very small initial grammar. We describe a language learner that extracts distributional information from a corpus annotated with parts of speech and is able to use this extracted information to accurately parse short sentences. The phrase structure learner is part of an ongoing project to determine just how much knowledge of language can be learned solely through distributional analysis.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 1992
Accession Number
ADA460382

Entities

People

  • Eric Brill
  • Mitchell Marcus

Organizations

  • University of Pennsylvania

Tags

DTIC Thesaurus Topics

  • Acquisition
  • Computational Linguistics
  • Computer Science
  • Context Free Grammars
  • Environment
  • Errors
  • Grammars
  • Information Operations
  • Information Science
  • Language
  • Linguistics
  • Natural Languages
  • New York
  • Probability
  • Probability Distributions
  • Statistics

Fields of Study

  • Linguistics

Readers

  • Computational Linguistics
  • Neural Network Machine Learning.