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

研究成果: Contribution to journal › Article › 査読

抄録

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.

本文言語英語
ページ（範囲）51-56
ページ数6
ジャーナルResearch Reports on Information Science and Electrical Engineering of Kyushu University
巻10
号1
出版ステータス出版済み - 3 1 2005

All Science Journal Classification (ASJC) codes

  • Computer Science(all)
  • Electrical and Electronic Engineering

フィンガープリント 「An evaluation of a layered neural network which have function of learning vectorial symbol representations on PP-attachment ambiguity resolution」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル