Structural parsing

C. Hoede, Lei Zhang

Research output: Book/ReportReportOther research output

16 Downloads (Pure)

Abstract

Parsing is an essential part of natural language processing. In this paper, structural parsing, which is based on the theory of knowledge graphs, is introduced. Under consideration of the semantic and syntactic features of natural language, both semantic and syntactic word graphs are formed. Grammar rules are derived from the syntactic word graphs. Due to the distinctions between Chinese and English, the grammar rules are given for the Chinese version and the English version of syntactic word graphs respectively. By traditional parsing a parse tree can then be given for a sentence, that can be used to map the sentence on a sentence graph. This is called structural parsing. The relationship with utterance paths is discussed. As a result, chunk indicators are proposed to guide structural parsing.
Original languageEnglish
Place of PublicationEnschede
PublisherUniversity of Twente, Department of Applied Mathematics
Number of pages39
Publication statusPublished - 2000

Publication series

NameMemoranda
PublisherDepartment of Applied Mathematics, University of Twente
No.1527
ISSN (Print)0169-2690

Fingerprint

Syntactics
Semantics
Processing

Keywords

  • MSC-05C99
  • IR-65715
  • EWI-3347
  • MSC-68F99

Cite this

Hoede, C., & Zhang, L. (2000). Structural parsing. (Memoranda; No. 1527). Enschede: University of Twente, Department of Applied Mathematics.
Hoede, C. ; Zhang, Lei. / Structural parsing. Enschede : University of Twente, Department of Applied Mathematics, 2000. 39 p. (Memoranda; 1527).
@book{72bed89d5d344e80a1edd5bd8c69ecae,
title = "Structural parsing",
abstract = "Parsing is an essential part of natural language processing. In this paper, structural parsing, which is based on the theory of knowledge graphs, is introduced. Under consideration of the semantic and syntactic features of natural language, both semantic and syntactic word graphs are formed. Grammar rules are derived from the syntactic word graphs. Due to the distinctions between Chinese and English, the grammar rules are given for the Chinese version and the English version of syntactic word graphs respectively. By traditional parsing a parse tree can then be given for a sentence, that can be used to map the sentence on a sentence graph. This is called structural parsing. The relationship with utterance paths is discussed. As a result, chunk indicators are proposed to guide structural parsing.",
keywords = "MSC-05C99, IR-65715, EWI-3347, MSC-68F99",
author = "C. Hoede and Lei Zhang",
note = "Imported from MEMORANDA",
year = "2000",
language = "English",
series = "Memoranda",
publisher = "University of Twente, Department of Applied Mathematics",
number = "1527",

}

Hoede, C & Zhang, L 2000, Structural parsing. Memoranda, no. 1527, University of Twente, Department of Applied Mathematics, Enschede.

Structural parsing. / Hoede, C.; Zhang, Lei.

Enschede : University of Twente, Department of Applied Mathematics, 2000. 39 p. (Memoranda; No. 1527).

Research output: Book/ReportReportOther research output

TY - BOOK

T1 - Structural parsing

AU - Hoede, C.

AU - Zhang, Lei

N1 - Imported from MEMORANDA

PY - 2000

Y1 - 2000

N2 - Parsing is an essential part of natural language processing. In this paper, structural parsing, which is based on the theory of knowledge graphs, is introduced. Under consideration of the semantic and syntactic features of natural language, both semantic and syntactic word graphs are formed. Grammar rules are derived from the syntactic word graphs. Due to the distinctions between Chinese and English, the grammar rules are given for the Chinese version and the English version of syntactic word graphs respectively. By traditional parsing a parse tree can then be given for a sentence, that can be used to map the sentence on a sentence graph. This is called structural parsing. The relationship with utterance paths is discussed. As a result, chunk indicators are proposed to guide structural parsing.

AB - Parsing is an essential part of natural language processing. In this paper, structural parsing, which is based on the theory of knowledge graphs, is introduced. Under consideration of the semantic and syntactic features of natural language, both semantic and syntactic word graphs are formed. Grammar rules are derived from the syntactic word graphs. Due to the distinctions between Chinese and English, the grammar rules are given for the Chinese version and the English version of syntactic word graphs respectively. By traditional parsing a parse tree can then be given for a sentence, that can be used to map the sentence on a sentence graph. This is called structural parsing. The relationship with utterance paths is discussed. As a result, chunk indicators are proposed to guide structural parsing.

KW - MSC-05C99

KW - IR-65715

KW - EWI-3347

KW - MSC-68F99

M3 - Report

T3 - Memoranda

BT - Structural parsing

PB - University of Twente, Department of Applied Mathematics

CY - Enschede

ER -

Hoede C, Zhang L. Structural parsing. Enschede: University of Twente, Department of Applied Mathematics, 2000. 39 p. (Memoranda; 1527).