Cross document ontology based information for multimedia retrieval

Dennis Reidsma; Jan Kuper; T. Declerck; H. Saggion; H. Cunningham

Cross document ontology based information for multimedia retrieval

Dennis Reidsma, Jan Kuper, T. Declerck, H. Saggion, H. Cunningham

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

30 Downloads (Pure)

Abstract

This paper describes the MUMIS project, which applies ontology based Information Extraction to improve the results of Information Retrieval in multimedia archives. It makes use of a domain specific ontology, multilingual lexicons and reasoning algorithms to automatically create a semantic annotation of sources. The innovative aspect is the use of a cross document merging algorithm that combines the information extracted from separate textual sources to produce an integrated, more complete, annotation of the material. This merging and unification process uses ontology based reasoning and scenarios which are extracted from annotated sources. The algorithms presented here have been implemented in a working demonstration prototype and have been applied on material from the Euro 2000 Soccer Championships

Original language	English
Title of host publication	Supplementary proceedings of the ICCS'03
Editors	B. Ganter, A. de Moor
Publisher	Shaker Publishing
Pages	73-86
ISBN (Print)	3-8322-1705-3
Publication status	Published - 19 Jul 2003
Event	International Conference on Computational Science 2003 - Saint Petersburg, Russian Federation Duration: 2 Jun 2003 → 4 Jun 2003

Conference

Conference	International Conference on Computational Science 2003
Abbreviated title	ICCS 2003
Country/Territory	Russian Federation
City	Saint Petersburg
Period	2/06/03 → 4/06/03

Keywords

METIS-215161

Access to Document

iccs03Final published version, 255 KB

Cite this

@inproceedings{57b0e3894bbd41deaf65c6edda969f93,

title = "Cross document ontology based information for multimedia retrieval",

abstract = "This paper describes the MUMIS project, which applies ontology based Information Extraction to improve the results of Information Retrieval in multimedia archives. It makes use of a domain specific ontology, multilingual lexicons and reasoning algorithms to automatically create a semantic annotation of sources. The innovative aspect is the use of a cross document merging algorithm that combines the information extracted from separate textual sources to produce an integrated, more complete, annotation of the material. This merging and unification process uses ontology based reasoning and scenarios which are extracted from annotated sources. The algorithms presented here have been implemented in a working demonstration prototype and have been applied on material from the Euro 2000 Soccer Championships",

keywords = "METIS-215161",

author = "Dennis Reidsma and Jan Kuper and T. Declerck and H. Saggion and H. Cunningham",

year = "2003",

month = jul,

day = "19",

language = "English",

isbn = "3-8322-1705-3",

pages = "73--86",

editor = "B. Ganter and {de Moor}, A.",

booktitle = "Supplementary proceedings of the ICCS'03",

publisher = "Shaker Publishing",

note = "International Conference on Computational Science 2003, ICCS 2003 ; Conference date: 02-06-2003 Through 04-06-2003",

}

TY - GEN

T1 - Cross document ontology based information for multimedia retrieval

AU - Reidsma, Dennis

AU - Kuper, Jan

AU - Declerck, T.

AU - Saggion, H.

AU - Cunningham, H.

PY - 2003/7/19

Y1 - 2003/7/19

N2 - This paper describes the MUMIS project, which applies ontology based Information Extraction to improve the results of Information Retrieval in multimedia archives. It makes use of a domain specific ontology, multilingual lexicons and reasoning algorithms to automatically create a semantic annotation of sources. The innovative aspect is the use of a cross document merging algorithm that combines the information extracted from separate textual sources to produce an integrated, more complete, annotation of the material. This merging and unification process uses ontology based reasoning and scenarios which are extracted from annotated sources. The algorithms presented here have been implemented in a working demonstration prototype and have been applied on material from the Euro 2000 Soccer Championships

AB - This paper describes the MUMIS project, which applies ontology based Information Extraction to improve the results of Information Retrieval in multimedia archives. It makes use of a domain specific ontology, multilingual lexicons and reasoning algorithms to automatically create a semantic annotation of sources. The innovative aspect is the use of a cross document merging algorithm that combines the information extracted from separate textual sources to produce an integrated, more complete, annotation of the material. This merging and unification process uses ontology based reasoning and scenarios which are extracted from annotated sources. The algorithms presented here have been implemented in a working demonstration prototype and have been applied on material from the Euro 2000 Soccer Championships

KW - METIS-215161

M3 - Conference contribution

SN - 3-8322-1705-3

SP - 73

EP - 86

BT - Supplementary proceedings of the ICCS'03

A2 - Ganter, B.

A2 - de Moor, A.

PB - Shaker Publishing

T2 - International Conference on Computational Science 2003

Y2 - 2 June 2003 through 4 June 2003

ER -

Cross document ontology based information for multimedia retrieval

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this