Estimation of the PCFG building the dependency constraint

Toshifumi Tanabe, Yoichi Tomiura, Toru Hitaka

Research output: Contribution to journalArticle

Abstract

In Natural Languages Processing, there are lots of syntax trees corresponding to an input sentence. If we can choose the correct syntax tree meaningfully, the quality of the processing is improved. We proposed the method of building the dependency constraint into a context free grammar by subdividing nonterminals according to the meaning of the phrase generated from the nonterminal and by grasping production rules from superordinate-subordinate relation of their meanings in the thesaurus. This paper shows estimation of the PCFG building the Dependency Constraint by the experiment of disambiguating which of N2 or N3 governs N1 in the noun phrase "N1 N2N3".

Original languageEnglish
Pages (from-to)93-97
Number of pages5
JournalResearch Reports on Information Science and Electrical Engineering of Kyushu University
Volume2
Issue number1
Publication statusPublished - Mar 1 1997

All Science Journal Classification (ASJC) codes

  • Computer Science(all)
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Estimation of the PCFG building the dependency constraint'. Together they form a unique fingerprint.

  • Cite this