AI Approaches to Statistical Language Models

Abstract

We have made a number of advances under this grant. We have created what is currently the most accurate parser for parsing into Penn-tree-bank-style trees; a program that identifies the antecedents of pronouns with 85% accuracy; a program that assigns function tags to parse text with 85% accuracy; a program that assigns referents to full noun phrases with 65% accuracy; very efficient parsers that explore very few constituents that do not appear in the final parse; and programs that discover semantic information about words from unlabeled text. Furthermore, all these programs work by statistical means.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Feb 15, 2000
Accession Number
ADA373537

Entities

People

  • Eugene Charniak

Organizations

  • Brown University

Tags

Communities of Interest

  • Autonomy

DTIC Thesaurus Topics

  • Accuracy
  • Artificial Intelligence
  • Classification
  • Computational Linguistics
  • Computer Science
  • Computers
  • Context Free Grammars
  • Grammars
  • Language
  • Linguistics
  • Natural Language Processing
  • Natural Languages
  • Universities

Fields of Study

  • Computer science

Readers

  • Computational Linguistics