Converting Dependency Structures to Phrase Structures

Abstract

Treebanks are of two types according to their annotation schemata: phrase-structure Treebanks such as the English Penn Treebank [8] and dependency Treebanks such as the Czech dependency Treebank [6]. Long before Treebanks were developed and widely used for natural language processing, there had been much discussion of comparison between dependency grammars and context-free phrase structure grammars [5]. In this paper, we address the relationship between dependency structures and phrase structures from a practical perspective; namely, the exploration of different algorithms that convert dependency structures to phrase structures and the evaluation of their performance against an existing Treebank. This work not only provides ways to convert Treebanks from one type of representation to the other, but also clarifies the differences in representational coverage of the two approaches.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 2001
Accession Number
ADA460498

Entities

People

  • Fei Xia
  • Martha Palmer

Organizations

  • University of Pennsylvania

Tags

Communities of Interest

  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Abstracts
  • Algorithms
  • Attachment
  • Construction
  • Conversion
  • Grammars
  • Information Operations
  • Information Science
  • Language
  • Machine Translation
  • Natural Language Processing
  • Natural Languages
  • Percolation
  • Phrase Structure Grammars
  • Precision
  • Standards

Fields of Study

  • Engineering

Readers

  • Computational Linguistics

Technology Areas

  • AI & ML
  • AI & ML - Machine Translation