Toward matching the relation instantiation from DB pedia ontology to wikipedia text: Fusing frame net to Korean

Younggyun Hahm; Jongsung Woo; Seongbae Park; Youngsik Kim; Jiwoo Seo; Dosam Hwang; Yousung Won; Jiseong Kim; Key Sun Choi

doi:10.1145/2660517.2660534

Toward matching the relation instantiation from DB pedia ontology to wikipedia text: Fusing frame net to Korean

Younggyun Hahm
, Jongsung Woo
, Seongbae Park
, Youngsik Kim
, Jiwoo Seo
, Dosam Hwang
, Yousung Won
, Jiseong Kim
, Key Sun Choi

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

3 Citations (Scopus)

Abstract

Nowadays, there are many ongoing researches to construct knowledge bases from unstructured data. This process requires an ontology that includes enough properties to cover the various attributes of knowledge elements. As a huge encyclopedia, Wikipedia is a typical unstructured corpora of knowledge. DBpedia, a structured knowledge base constructed from Wikipedia, is based on DBpedia ontology which was created to represent knowledge in Wikipedia well. However, DBpedia ontology is a Wikipedia-Infobox-driven ontology. This means that although it is suitable to represent essential knowledge of Wikipedia, it does not cover all of the knowledge in Wikipedia text. In overcoming this problem, resources representing semantics or relations of words such as WordNet1 and FrameNet2 are considered useful. In this paper we determined whether DBpedia ontology is enough to cover a sufficient amount of natural language written knowledge in Wikipedia. We mainly focused on the Korean Wikipedia, and calculated the Korean Wikipedia coverage rate with two methods, by the DBpedia ontology and by FrameNet frames. To do this, we extracted sentences with extractable knowledge from Wikipedia text, and also extracted natural language predicates by Part-Of-Speech tagging. We generated Korean lexicons for DBpedia ontology properties and frame indexes, and used these lexicons to measure the Korean Wikipedia coverage ratio of the DBpedia ontology and frames. By our measurements, FrameNet frames cover 73.85% of the Korean Wikipedia sentences, which is a sufficient portion of Wikipedia text. We finally show the limitations of DBpedia and FrameNet briefly, and propose the outlook of constructing knowledge bases based on the experiment results.

Original language	English
Title of host publication	Proceedings of the 10th International Conference on Semantic Systems, SEMANTiCS 2014
Editors	Harald Sack, Agata Filipowska, Jens Lehmann, Sebastian Hellmann
Publisher	Association for Computing Machinery
Pages	13-19
Number of pages	7
Edition	September
ISBN (Electronic)	9781450329279, 9781450329804
DOIs	https://doi.org/10.1145/2660517.2660534
Publication status	Published - 4 Sept 2014
Event	10th International Conference on Semantic Systems, SEMANTiCS 2014 - Leipzig, Germany Duration: 4 Sept 2014 → 5 Sept 2014

Publication series

Name	ACM International Conference Proceeding Series
Number	September
Volume	2014-September

Conference

Conference	10th International Conference on Semantic Systems, SEMANTiCS 2014
Country/Territory	Germany
City	Leipzig
Period	4/09/14 → 5/09/14

Bibliographical note

Publisher Copyright:
Copyright © 2014 by the Association for Computing Machinery, Inc.

Keywords

Dbpedia
Framenet
Knowledge representation
Ontology
Wikipedia

Access to Document

10.1145/2660517.2660534

Cite this

Hahm, Y., Woo, J., Park, S., Kim, Y., Seo, J., Hwang, D., Won, Y., Kim, J., & Choi, K. S. (2014). Toward matching the relation instantiation from DB pedia ontology to wikipedia text: Fusing frame net to Korean. In H. Sack, A. Filipowska, J. Lehmann, & S. Hellmann (Eds.), Proceedings of the 10th International Conference on Semantic Systems, SEMANTiCS 2014 (September ed., pp. 13-19). (ACM International Conference Proceeding Series; Vol. 2014-September, No. September). Association for Computing Machinery. https://doi.org/10.1145/2660517.2660534

Hahm, Younggyun ; Woo, Jongsung ; Park, Seongbae et al. / Toward matching the relation instantiation from DB pedia ontology to wikipedia text : Fusing frame net to Korean. Proceedings of the 10th International Conference on Semantic Systems, SEMANTiCS 2014. editor / Harald Sack ; Agata Filipowska ; Jens Lehmann ; Sebastian Hellmann. September. ed. Association for Computing Machinery, 2014. pp. 13-19 (ACM International Conference Proceeding Series; September).

@inproceedings{093d9d23a0ff4ac09d538e0021ec0742,

title = "Toward matching the relation instantiation from DB pedia ontology to wikipedia text: Fusing frame net to Korean",

abstract = "Nowadays, there are many ongoing researches to construct knowledge bases from unstructured data. This process requires an ontology that includes enough properties to cover the various attributes of knowledge elements. As a huge encyclopedia, Wikipedia is a typical unstructured corpora of knowledge. DBpedia, a structured knowledge base constructed from Wikipedia, is based on DBpedia ontology which was created to represent knowledge in Wikipedia well. However, DBpedia ontology is a Wikipedia-Infobox-driven ontology. This means that although it is suitable to represent essential knowledge of Wikipedia, it does not cover all of the knowledge in Wikipedia text. In overcoming this problem, resources representing semantics or relations of words such as WordNet1 and FrameNet2 are considered useful. In this paper we determined whether DBpedia ontology is enough to cover a sufficient amount of natural language written knowledge in Wikipedia. We mainly focused on the Korean Wikipedia, and calculated the Korean Wikipedia coverage rate with two methods, by the DBpedia ontology and by FrameNet frames. To do this, we extracted sentences with extractable knowledge from Wikipedia text, and also extracted natural language predicates by Part-Of-Speech tagging. We generated Korean lexicons for DBpedia ontology properties and frame indexes, and used these lexicons to measure the Korean Wikipedia coverage ratio of the DBpedia ontology and frames. By our measurements, FrameNet frames cover 73.85\% of the Korean Wikipedia sentences, which is a sufficient portion of Wikipedia text. We finally show the limitations of DBpedia and FrameNet briefly, and propose the outlook of constructing knowledge bases based on the experiment results.",

keywords = "Dbpedia, Framenet, Knowledge representation, Ontology, Wikipedia",

author = "Younggyun Hahm and Jongsung Woo and Seongbae Park and Youngsik Kim and Jiwoo Seo and Dosam Hwang and Yousung Won and Jiseong Kim and Choi, \{Key Sun\}",

note = "Publisher Copyright: Copyright {\textcopyright} 2014 by the Association for Computing Machinery, Inc.; 10th International Conference on Semantic Systems, SEMANTiCS 2014 ; Conference date: 04-09-2014 Through 05-09-2014",

year = "2014",

month = sep,

day = "4",

doi = "10.1145/2660517.2660534",

language = "English",

series = "ACM International Conference Proceeding Series",

publisher = "Association for Computing Machinery",

number = "September",

pages = "13--19",

editor = "Harald Sack and Agata Filipowska and Jens Lehmann and Sebastian Hellmann",

booktitle = "Proceedings of the 10th International Conference on Semantic Systems, SEMANTiCS 2014",

edition = "September",

}

Hahm, Y, Woo, J, Park, S, Kim, Y, Seo, J, Hwang, D, Won, Y, Kim, J & Choi, KS 2014, Toward matching the relation instantiation from DB pedia ontology to wikipedia text: Fusing frame net to Korean. in H Sack, A Filipowska, J Lehmann & S Hellmann (eds), Proceedings of the 10th International Conference on Semantic Systems, SEMANTiCS 2014. September edn, ACM International Conference Proceeding Series, no. September, vol. 2014-September, Association for Computing Machinery, pp. 13-19, 10th International Conference on Semantic Systems, SEMANTiCS 2014, Leipzig, Germany, 4/09/14. https://doi.org/10.1145/2660517.2660534

Toward matching the relation instantiation from DB pedia ontology to wikipedia text: Fusing frame net to Korean. / Hahm, Younggyun; Woo, Jongsung; Park, Seongbae et al.
Proceedings of the 10th International Conference on Semantic Systems, SEMANTiCS 2014. ed. / Harald Sack; Agata Filipowska; Jens Lehmann; Sebastian Hellmann. September. ed. Association for Computing Machinery, 2014. p. 13-19 (ACM International Conference Proceeding Series; Vol. 2014-September, No. September).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Toward matching the relation instantiation from DB pedia ontology to wikipedia text

T2 - 10th International Conference on Semantic Systems, SEMANTiCS 2014

AU - Hahm, Younggyun

AU - Woo, Jongsung

AU - Park, Seongbae

AU - Kim, Youngsik

AU - Seo, Jiwoo

AU - Hwang, Dosam

AU - Won, Yousung

AU - Kim, Jiseong

AU - Choi, Key Sun

PY - 2014/9/4

Y1 - 2014/9/4

N2 - Nowadays, there are many ongoing researches to construct knowledge bases from unstructured data. This process requires an ontology that includes enough properties to cover the various attributes of knowledge elements. As a huge encyclopedia, Wikipedia is a typical unstructured corpora of knowledge. DBpedia, a structured knowledge base constructed from Wikipedia, is based on DBpedia ontology which was created to represent knowledge in Wikipedia well. However, DBpedia ontology is a Wikipedia-Infobox-driven ontology. This means that although it is suitable to represent essential knowledge of Wikipedia, it does not cover all of the knowledge in Wikipedia text. In overcoming this problem, resources representing semantics or relations of words such as WordNet1 and FrameNet2 are considered useful. In this paper we determined whether DBpedia ontology is enough to cover a sufficient amount of natural language written knowledge in Wikipedia. We mainly focused on the Korean Wikipedia, and calculated the Korean Wikipedia coverage rate with two methods, by the DBpedia ontology and by FrameNet frames. To do this, we extracted sentences with extractable knowledge from Wikipedia text, and also extracted natural language predicates by Part-Of-Speech tagging. We generated Korean lexicons for DBpedia ontology properties and frame indexes, and used these lexicons to measure the Korean Wikipedia coverage ratio of the DBpedia ontology and frames. By our measurements, FrameNet frames cover 73.85% of the Korean Wikipedia sentences, which is a sufficient portion of Wikipedia text. We finally show the limitations of DBpedia and FrameNet briefly, and propose the outlook of constructing knowledge bases based on the experiment results.

AB - Nowadays, there are many ongoing researches to construct knowledge bases from unstructured data. This process requires an ontology that includes enough properties to cover the various attributes of knowledge elements. As a huge encyclopedia, Wikipedia is a typical unstructured corpora of knowledge. DBpedia, a structured knowledge base constructed from Wikipedia, is based on DBpedia ontology which was created to represent knowledge in Wikipedia well. However, DBpedia ontology is a Wikipedia-Infobox-driven ontology. This means that although it is suitable to represent essential knowledge of Wikipedia, it does not cover all of the knowledge in Wikipedia text. In overcoming this problem, resources representing semantics or relations of words such as WordNet1 and FrameNet2 are considered useful. In this paper we determined whether DBpedia ontology is enough to cover a sufficient amount of natural language written knowledge in Wikipedia. We mainly focused on the Korean Wikipedia, and calculated the Korean Wikipedia coverage rate with two methods, by the DBpedia ontology and by FrameNet frames. To do this, we extracted sentences with extractable knowledge from Wikipedia text, and also extracted natural language predicates by Part-Of-Speech tagging. We generated Korean lexicons for DBpedia ontology properties and frame indexes, and used these lexicons to measure the Korean Wikipedia coverage ratio of the DBpedia ontology and frames. By our measurements, FrameNet frames cover 73.85% of the Korean Wikipedia sentences, which is a sufficient portion of Wikipedia text. We finally show the limitations of DBpedia and FrameNet briefly, and propose the outlook of constructing knowledge bases based on the experiment results.

KW - Dbpedia

KW - Framenet

KW - Knowledge representation

KW - Ontology

KW - Wikipedia

UR - https://www.scopus.com/pages/publications/84937705387

U2 - 10.1145/2660517.2660534

DO - 10.1145/2660517.2660534

M3 - Conference contribution

AN - SCOPUS:84937705387

T3 - ACM International Conference Proceeding Series

SP - 13

EP - 19

BT - Proceedings of the 10th International Conference on Semantic Systems, SEMANTiCS 2014

A2 - Sack, Harald

A2 - Filipowska, Agata

A2 - Lehmann, Jens

A2 - Hellmann, Sebastian

PB - Association for Computing Machinery

Y2 - 4 September 2014 through 5 September 2014

ER -

Hahm Y, Woo J, Park S, Kim Y, Seo J, Hwang D et al. Toward matching the relation instantiation from DB pedia ontology to wikipedia text: Fusing frame net to Korean. In Sack H, Filipowska A, Lehmann J, Hellmann S, editors, Proceedings of the 10th International Conference on Semantic Systems, SEMANTiCS 2014. September ed. Association for Computing Machinery. 2014. p. 13-19. (ACM International Conference Proceeding Series; September). doi: 10.1145/2660517.2660534

Toward matching the relation instantiation from DB pedia ontology to wikipedia text: Fusing frame net to Korean

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this