Language modeling using patterns extracted from parse trees for speech recognition

Takatoshi Jitsuhiro*, Hirofumi Yamamoto, Setsuo Yamada, Genichiro Kikui, Yoshinori Sagisaka

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review


We propose new language models to represent phrasal structures by patterns extracted from parse trees. First, modified word trigram models are proposed. They are extracted from sentences analyzed by the preprocessing of the parser with knowledge. Since sentences are analyzed to create sub-trees of a few words, these trigram models can represent relations among a few neighbor words more strongly than conventional word trigram models. Second, word pattern models are used on these modified word trigram models. The word patterns are extracted from parse trees and can represent phrasal structures and much longer word-dependency than trigram models. Experimental results show that modified trigram models are more effective than traditional trigram models and that pattern models attain slight improvements over modified trigram models. Furthermore, additional experiments show that pattern models are more effective for long sentences.

Original languageEnglish
Pages (from-to)446-453
Number of pages8
JournalIEICE Transactions on Information and Systems
Issue number3
Publication statusPublished - 2003 Mar
Externally publishedYes


  • Language model
  • N-gram model
  • Parser
  • Pattern model
  • Speech recognition

ASJC Scopus subject areas

  • Software
  • Hardware and Architecture
  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering
  • Artificial Intelligence


Dive into the research topics of 'Language modeling using patterns extracted from parse trees for speech recognition'. Together they form a unique fingerprint.

Cite this