An Evaluation of a Layered Neural Network which Have Function of Learning Vectorial Symbol Representations on PP-attachment Ambiguity Resolution - Collections

＜departmental bulletin paper＞
An Evaluation of a Layered Neural Network which Have Function of Learning Vectorial Symbol Representations on PP-attachment Ambiguity Resolution

Creator	Creator Name 本木, 実 Motoki, Minoru モトキ, ミノル Affiliation Affiliation Name 九州大学大学院システム情報科学府知能システム学専攻 : 博士後期課程 Department of Intelligent Systems, Graduate School of Information Science and Electrical Engineering, Kyushu University : Doctoral Program
	Creator Name 冨浦, 洋一 Tomiura, Yoichi トミウラ, ヨウイチ Affiliation Affiliation Name 九州大学大学院システム情報科学研究院知能システム学部門 Department of Intelligent Systems, Faculty of Information Science and Electrical Engineering, Kyushu University
	Creator Name 日高, 達 Hitaka, Toru ヒタカ, トオル Affiliation Affiliation Name 九州大学名誉教授 Professor Emeritus, Kyushu University
	Creator Name 嶋津, 好生 Shimazu, Yoshio シマヅ, ヨシオ Affiliation Affiliation Name 九州産業大学工学部電気工学科 Department of Electrical Engineering, School of Engineering, Kyushu Sangyo University
	Creator Name 高橋, 直人 Takahashi, Naoto タカハシ, ナオト Affiliation Affiliation Name 独立行政法人産業技術総合研究所(AIST) National Institute of Advanced Industrial Science and Technology
Language	Japanese
Publisher	九州大学大学院システム情報科学研究院
Publisher	Faculty of Information Science and Electrical Engineering, Kyushu University
Date	2005-03-25
Source Title	Research reports on information science and electrical engineering of Kyushu University
Vol	10
Issue	1
First Page	51
Last Page	56
Publication Type	Version of Record
Access Rights	open access
JaLC DOI	https://doi.org/10.15017/1516061
Related DOI	https://portal.isee.kyushu-u.ac.jp/
Related URI	https://portal.isee.kyushu-u.ac.jp/
Relation	https://portal.isee.kyushu-u.ac.jp/
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 w...eight 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.show more

Hide fulltext details.

File	FileType	Size	Views	Description
p051	pdf	1.81 MB	231

Details

PISSN	1342-3819
EISSN	2188-0891
NCID	AN10569524
Record ID	1516061
Peer-Reviewed	Refereed
Subject Terms	PP-attachment
	英語前置詞句係り先決定問題
	Neural network
	ニューラルネット
	Vectorial symbol representation
	記号表現ベクトル
Created Date	2015.06.08
Modified Date	2020.12.09

Export

Link to this page

Search Other Services

Statistics

＜departmental bulletin paper＞ An Evaluation of a Layered Neural Network which Have Function of Learning Vectorial Symbol Representations on PP-attachment Ambiguity Resolution

Hide fulltext details.

Details

People who viewed this item also viewed

＜departmental bulletin paper＞
An Evaluation of a Layered Neural Network which Have Function of Learning Vectorial Symbol Representations on PP-attachment Ambiguity Resolution