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

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

Intelligence Science

Research output: Contribution to journal › Article › peer-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 language	English
Pages (from-to)	51-56
Number of pages	6
Journal	Research Reports on Information Science and Electrical Engineering of Kyushu University
Volume	10
Issue number	1
Publication status	Published - Mar 2005

All Science Journal Classification (ASJC) codes

Computer Science(all)
Electrical and Electronic Engineering

Cite this

An evaluation of a layered neural network which have function of learning vectorial symbol representations on PP-attachment ambiguity resolution. / Motoki, Minoru; Tomiura, Yoichi; Hitaka, Toru et al.
In: Research Reports on Information Science and Electrical Engineering of Kyushu University, Vol. 10, No. 1, 03.2005, p. 51-56.

Research output: Contribution to journal › Article › peer-review

@article{0170a8a529354750be160e30c4f25c82,

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

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.",

author = "Minoru Motoki and Yoichi Tomiura and Toru Hitaka and Yoshio Shimazu and Naoto Takahashi",

year = "2005",

month = mar,

language = "English",

volume = "10",

pages = "51--56",

journal = "Research Reports on Information Science and Electrical Engineering of Kyushu University",

issn = "1342-3819",

publisher = "Kyushu University, Faculty of Science",

number = "1",

}

TY - JOUR

T1 - An evaluation of a layered neural network which have function of learning vectorial symbol representations on PP-attachment ambiguity resolution

AU - Motoki, Minoru

AU - Tomiura, Yoichi

AU - Hitaka, Toru

AU - Shimazu, Yoshio

AU - Takahashi, Naoto

PY - 2005/3

Y1 - 2005/3

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=23744463889&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=23744463889&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:23744463889

SN - 1342-3819

VL - 10

SP - 51

EP - 56

JO - Research Reports on Information Science and Electrical Engineering of Kyushu University

JF - Research Reports on Information Science and Electrical Engineering of Kyushu University

IS - 1

ER -

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

Abstract

All Science Journal Classification (ASJC) codes

Other files and links

Fingerprint

Cite this