A proposal for a method of graph ontology by automatically extracting relationships between captions and X- and Y-axis titles

Sarunya Kanjanawattana, Masaomi Kimura

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

A two dimensional graph is a powerful method for representing a set of objects that usually appears in many sources of literature. Numerous efforts have been made to discover image semantics based on contents of literature. However, conventional methods have not been fully able to satisfy users because a wide variety of techniques are being developed, and each is very useful for enhancing system capabilities in their own way. In this paper, we have developed a method to automatically extract relationships from graphs on the basic of their captions and image content, particularly from graph titles. Furthermore, we improved our idea by applying several technologies such as ontology and a dependency parser. The relationships discovered in a graph are presented in the form of a triple (subject, predicate, object). Our objectives are to find implicit and explicit information in the graph and reduce the semantic gap between an image and literature context. Accuracy was manually estimated to identify the most reliable triple. Based on our results, we concluded that the accuracy via our method was acceptable. Therefore, our method is dependable and worthy of future development.

LanguageEnglish
Title of host publicationKEOD
PublisherSciTePress
Pages231-238
Number of pages8
Volume2
ISBN (Print)9789897581588
StatePublished - 2015
Event7th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management, IC3K 2015 - Lisbon, Portugal
Duration: 2015 Nov 122015 Nov 14

Other

Other7th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management, IC3K 2015
CountryPortugal
CityLisbon
Period15/11/1215/11/14

Fingerprint

Ontology
Semantics

Keywords

  • Dependency Parser
  • Edit Distance
  • OCR
  • Ontology
  • Relationship
  • Triple

ASJC Scopus subject areas

  • Software

Cite this

A proposal for a method of graph ontology by automatically extracting relationships between captions and X- and Y-axis titles. / Kanjanawattana, Sarunya; Kimura, Masaomi.

KEOD. Vol. 2 SciTePress, 2015. p. 231-238.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Kanjanawattana, S & Kimura, M 2015, A proposal for a method of graph ontology by automatically extracting relationships between captions and X- and Y-axis titles. in KEOD. vol. 2, SciTePress, pp. 231-238, 7th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management, IC3K 2015, Lisbon, Portugal, 15/11/12.
@inproceedings{a3aad3c4070e472ba0552b6ab7c0f631,
title = "A proposal for a method of graph ontology by automatically extracting relationships between captions and X- and Y-axis titles",
abstract = "A two dimensional graph is a powerful method for representing a set of objects that usually appears in many sources of literature. Numerous efforts have been made to discover image semantics based on contents of literature. However, conventional methods have not been fully able to satisfy users because a wide variety of techniques are being developed, and each is very useful for enhancing system capabilities in their own way. In this paper, we have developed a method to automatically extract relationships from graphs on the basic of their captions and image content, particularly from graph titles. Furthermore, we improved our idea by applying several technologies such as ontology and a dependency parser. The relationships discovered in a graph are presented in the form of a triple (subject, predicate, object). Our objectives are to find implicit and explicit information in the graph and reduce the semantic gap between an image and literature context. Accuracy was manually estimated to identify the most reliable triple. Based on our results, we concluded that the accuracy via our method was acceptable. Therefore, our method is dependable and worthy of future development.",
keywords = "Dependency Parser, Edit Distance, OCR, Ontology, Relationship, Triple",
author = "Sarunya Kanjanawattana and Masaomi Kimura",
year = "2015",
language = "English",
isbn = "9789897581588",
volume = "2",
pages = "231--238",
booktitle = "KEOD",
publisher = "SciTePress",

}

TY - GEN

T1 - A proposal for a method of graph ontology by automatically extracting relationships between captions and X- and Y-axis titles

AU - Kanjanawattana,Sarunya

AU - Kimura,Masaomi

PY - 2015

Y1 - 2015

N2 - A two dimensional graph is a powerful method for representing a set of objects that usually appears in many sources of literature. Numerous efforts have been made to discover image semantics based on contents of literature. However, conventional methods have not been fully able to satisfy users because a wide variety of techniques are being developed, and each is very useful for enhancing system capabilities in their own way. In this paper, we have developed a method to automatically extract relationships from graphs on the basic of their captions and image content, particularly from graph titles. Furthermore, we improved our idea by applying several technologies such as ontology and a dependency parser. The relationships discovered in a graph are presented in the form of a triple (subject, predicate, object). Our objectives are to find implicit and explicit information in the graph and reduce the semantic gap between an image and literature context. Accuracy was manually estimated to identify the most reliable triple. Based on our results, we concluded that the accuracy via our method was acceptable. Therefore, our method is dependable and worthy of future development.

AB - A two dimensional graph is a powerful method for representing a set of objects that usually appears in many sources of literature. Numerous efforts have been made to discover image semantics based on contents of literature. However, conventional methods have not been fully able to satisfy users because a wide variety of techniques are being developed, and each is very useful for enhancing system capabilities in their own way. In this paper, we have developed a method to automatically extract relationships from graphs on the basic of their captions and image content, particularly from graph titles. Furthermore, we improved our idea by applying several technologies such as ontology and a dependency parser. The relationships discovered in a graph are presented in the form of a triple (subject, predicate, object). Our objectives are to find implicit and explicit information in the graph and reduce the semantic gap between an image and literature context. Accuracy was manually estimated to identify the most reliable triple. Based on our results, we concluded that the accuracy via our method was acceptable. Therefore, our method is dependable and worthy of future development.

KW - Dependency Parser

KW - Edit Distance

KW - OCR

KW - Ontology

KW - Relationship

KW - Triple

UR - http://www.scopus.com/inward/record.url?scp=84961135233&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84961135233&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9789897581588

VL - 2

SP - 231

EP - 238

BT - KEOD

PB - SciTePress

ER -