A semantic orthogonal mapping method through deep-learning for semantic computing

Xing Chen, Yasushi Kiyoki

研究成果: Conference contribution

抄録

In order to realize an artificial intelligent system, a basic mechanism should be provided for expressing and processing the semantic. We have presented semantic computing models in which original data are mapped in to a semantic space and presented as points in semantic spaces. That is, we presented a method to process semantic information by calculating Euclidean distances of those points in the semantic spaces. In our continuous studies, we note that different mapping matrixes are required to map the original data in to the semantic space when this model is applied in different application areas. Therefore, it is an important research topic to develop methods to create the mapping matrixes applied in different areas. Many research works are presented on applying the model in the areas of semantic information retrieving, semantic information classifying, semantic information extracting, and semantic information analyzing on reason and results, etc. In these works, the mapping matrixes are created based on the analyzations in the application areas with human knowledge. In this paper, we present a new method to perform the semantic mapping through deep-learning computation. The most important feature of our method is that we implement semantic mapping through training data sets rather than the mapping matrix which is created based on the analyzations of human being. We first discuss five basic operations, the semantic space creation, semantic mapping, semantic mapping matrix, semantic space expansion and contraction. After that, we present our method. In order to present correlations of the semantic information correctly in Euclidean distances, the axes of a semantic space must be orthogonal to each other. Therefore, we also discuss how to implement semantic orthogonal mapping. We believe that our study will open new application areas on semantic computing and deep-learning.

元の言語English
ホスト出版物のタイトルInformation Modelling and Knowledge Bases XXX
編集者Tatiana Endrjukaite, Hannu Jaakkola, Alexander Dudko, Yasushi Kiyoki, Bernhard Thalheim, Naofumi Yoshida
出版者IOS Press
ページ39-60
ページ数22
ISBN(電子版)9781614999324
DOI
出版物ステータスPublished - 2019 1 1

出版物シリーズ

名前Frontiers in Artificial Intelligence and Applications
312
ISSN(印刷物)0922-6389

Fingerprint

Semantics
Deep learning
Intelligent systems

ASJC Scopus subject areas

  • Artificial Intelligence

これを引用

Chen, X., & Kiyoki, Y. (2019). A semantic orthogonal mapping method through deep-learning for semantic computing. : T. Endrjukaite, H. Jaakkola, A. Dudko, Y. Kiyoki, B. Thalheim, & N. Yoshida (版), Information Modelling and Knowledge Bases XXX (pp. 39-60). (Frontiers in Artificial Intelligence and Applications; 巻数 312). IOS Press. https://doi.org/10.3233/978-1-61499-933-1-39

A semantic orthogonal mapping method through deep-learning for semantic computing. / Chen, Xing; Kiyoki, Yasushi.

Information Modelling and Knowledge Bases XXX. 版 / Tatiana Endrjukaite; Hannu Jaakkola; Alexander Dudko; Yasushi Kiyoki; Bernhard Thalheim; Naofumi Yoshida. IOS Press, 2019. p. 39-60 (Frontiers in Artificial Intelligence and Applications; 巻 312).

研究成果: Conference contribution

Chen, X & Kiyoki, Y 2019, A semantic orthogonal mapping method through deep-learning for semantic computing. : T Endrjukaite, H Jaakkola, A Dudko, Y Kiyoki, B Thalheim & N Yoshida (版), Information Modelling and Knowledge Bases XXX. Frontiers in Artificial Intelligence and Applications, 巻. 312, IOS Press, pp. 39-60. https://doi.org/10.3233/978-1-61499-933-1-39
Chen X, Kiyoki Y. A semantic orthogonal mapping method through deep-learning for semantic computing. : Endrjukaite T, Jaakkola H, Dudko A, Kiyoki Y, Thalheim B, Yoshida N, 編集者, Information Modelling and Knowledge Bases XXX. IOS Press. 2019. p. 39-60. (Frontiers in Artificial Intelligence and Applications). https://doi.org/10.3233/978-1-61499-933-1-39
Chen, Xing ; Kiyoki, Yasushi. / A semantic orthogonal mapping method through deep-learning for semantic computing. Information Modelling and Knowledge Bases XXX. 編集者 / Tatiana Endrjukaite ; Hannu Jaakkola ; Alexander Dudko ; Yasushi Kiyoki ; Bernhard Thalheim ; Naofumi Yoshida. IOS Press, 2019. pp. 39-60 (Frontiers in Artificial Intelligence and Applications).
@inproceedings{351ac31ba2f443f5bf94be3dfe7bdcfd,
title = "A semantic orthogonal mapping method through deep-learning for semantic computing",
abstract = "In order to realize an artificial intelligent system, a basic mechanism should be provided for expressing and processing the semantic. We have presented semantic computing models in which original data are mapped in to a semantic space and presented as points in semantic spaces. That is, we presented a method to process semantic information by calculating Euclidean distances of those points in the semantic spaces. In our continuous studies, we note that different mapping matrixes are required to map the original data in to the semantic space when this model is applied in different application areas. Therefore, it is an important research topic to develop methods to create the mapping matrixes applied in different areas. Many research works are presented on applying the model in the areas of semantic information retrieving, semantic information classifying, semantic information extracting, and semantic information analyzing on reason and results, etc. In these works, the mapping matrixes are created based on the analyzations in the application areas with human knowledge. In this paper, we present a new method to perform the semantic mapping through deep-learning computation. The most important feature of our method is that we implement semantic mapping through training data sets rather than the mapping matrix which is created based on the analyzations of human being. We first discuss five basic operations, the semantic space creation, semantic mapping, semantic mapping matrix, semantic space expansion and contraction. After that, we present our method. In order to present correlations of the semantic information correctly in Euclidean distances, the axes of a semantic space must be orthogonal to each other. Therefore, we also discuss how to implement semantic orthogonal mapping. We believe that our study will open new application areas on semantic computing and deep-learning.",
keywords = "artificial intelligent, deep-learning computation, Semantic computing, semantic mapping, semantic space",
author = "Xing Chen and Yasushi Kiyoki",
year = "2019",
month = "1",
day = "1",
doi = "10.3233/978-1-61499-933-1-39",
language = "English",
series = "Frontiers in Artificial Intelligence and Applications",
publisher = "IOS Press",
pages = "39--60",
editor = "Tatiana Endrjukaite and Hannu Jaakkola and Alexander Dudko and Yasushi Kiyoki and Bernhard Thalheim and Naofumi Yoshida",
booktitle = "Information Modelling and Knowledge Bases XXX",

}

TY - GEN

T1 - A semantic orthogonal mapping method through deep-learning for semantic computing

AU - Chen, Xing

AU - Kiyoki, Yasushi

PY - 2019/1/1

Y1 - 2019/1/1

N2 - In order to realize an artificial intelligent system, a basic mechanism should be provided for expressing and processing the semantic. We have presented semantic computing models in which original data are mapped in to a semantic space and presented as points in semantic spaces. That is, we presented a method to process semantic information by calculating Euclidean distances of those points in the semantic spaces. In our continuous studies, we note that different mapping matrixes are required to map the original data in to the semantic space when this model is applied in different application areas. Therefore, it is an important research topic to develop methods to create the mapping matrixes applied in different areas. Many research works are presented on applying the model in the areas of semantic information retrieving, semantic information classifying, semantic information extracting, and semantic information analyzing on reason and results, etc. In these works, the mapping matrixes are created based on the analyzations in the application areas with human knowledge. In this paper, we present a new method to perform the semantic mapping through deep-learning computation. The most important feature of our method is that we implement semantic mapping through training data sets rather than the mapping matrix which is created based on the analyzations of human being. We first discuss five basic operations, the semantic space creation, semantic mapping, semantic mapping matrix, semantic space expansion and contraction. After that, we present our method. In order to present correlations of the semantic information correctly in Euclidean distances, the axes of a semantic space must be orthogonal to each other. Therefore, we also discuss how to implement semantic orthogonal mapping. We believe that our study will open new application areas on semantic computing and deep-learning.

AB - In order to realize an artificial intelligent system, a basic mechanism should be provided for expressing and processing the semantic. We have presented semantic computing models in which original data are mapped in to a semantic space and presented as points in semantic spaces. That is, we presented a method to process semantic information by calculating Euclidean distances of those points in the semantic spaces. In our continuous studies, we note that different mapping matrixes are required to map the original data in to the semantic space when this model is applied in different application areas. Therefore, it is an important research topic to develop methods to create the mapping matrixes applied in different areas. Many research works are presented on applying the model in the areas of semantic information retrieving, semantic information classifying, semantic information extracting, and semantic information analyzing on reason and results, etc. In these works, the mapping matrixes are created based on the analyzations in the application areas with human knowledge. In this paper, we present a new method to perform the semantic mapping through deep-learning computation. The most important feature of our method is that we implement semantic mapping through training data sets rather than the mapping matrix which is created based on the analyzations of human being. We first discuss five basic operations, the semantic space creation, semantic mapping, semantic mapping matrix, semantic space expansion and contraction. After that, we present our method. In order to present correlations of the semantic information correctly in Euclidean distances, the axes of a semantic space must be orthogonal to each other. Therefore, we also discuss how to implement semantic orthogonal mapping. We believe that our study will open new application areas on semantic computing and deep-learning.

KW - artificial intelligent

KW - deep-learning computation

KW - Semantic computing

KW - semantic mapping

KW - semantic space

UR - http://www.scopus.com/inward/record.url?scp=85059582994&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85059582994&partnerID=8YFLogxK

U2 - 10.3233/978-1-61499-933-1-39

DO - 10.3233/978-1-61499-933-1-39

M3 - Conference contribution

AN - SCOPUS:85059582994

T3 - Frontiers in Artificial Intelligence and Applications

SP - 39

EP - 60

BT - Information Modelling and Knowledge Bases XXX

A2 - Endrjukaite, Tatiana

A2 - Jaakkola, Hannu

A2 - Dudko, Alexander

A2 - Kiyoki, Yasushi

A2 - Thalheim, Bernhard

A2 - Yoshida, Naofumi

PB - IOS Press

ER -