An evaluation of a layered neural network which have function of learning vectorial symbol representations on PP-attachment ambiguity resolution

Minoru Motoki, Yoichi Tomiura, Toru Hitaka, Yoshio Shimazu, Naoto Takahashi

Research output: Contribution to journalArticlepeer-review

Abstract

This paper describes a PP-attachment ambiguity resolution with a layered neural network which have function of learning vectorial symbol representations. The proposed model does not update only link weight but also vectorial symbol representations. We show qualitative difference between a proposed model and an ordinary layered neural network, which has more hidden units (i.e. more parameters) to have more flexibility but does not update symbol representations.

Original languageEnglish
Pages (from-to)51-56
Number of pages6
JournalResearch Reports on Information Science and Electrical Engineering of Kyushu University
Volume10
Issue number1
Publication statusPublished - Mar 1 2005

All Science Journal Classification (ASJC) codes

  • Computer Science(all)
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'An evaluation of a layered neural network which have function of learning vectorial symbol representations on PP-attachment ambiguity resolution'. Together they form a unique fingerprint.

Cite this