Enhancing enterprise knowledge processes via cross-media extraction

Jose Iria, Victoria Uren, Alberto Lavelli, Sebastian Blohm, Aba-sah Dadzie, Thomas Franz, Ioannis Kompatsiaris, Joao Magalhaes, Spiros Nikolopoulos, Christine Preisach, Piercarlo Slavazza

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

Abstract

In large organizations the resources needed to solve challenging problems are typically dispersed over systems within and beyond the organization, and also in different media. However, there is still the need, in knowledge environments, for extraction methods able to combine evidence for a fact from across different media. In many cases the whole is more than the sum of its parts: only when considering the different media simultaneously can enough evidence be obtained to derive facts otherwise inaccessible to the knowledge worker via traditional methods that work on each single medium separately. In this paper, we present a cross-media knowledge extraction framework specifically designed to handle large volumes of documents composed of three types of media text, images and raw data and to exploit the evidence across the media. Our goal is to improve the quality and depth of automatically extracted knowledge.
Original languageEnglish
Title of host publicationK-CAP '07 - proceedings of the 4th international conference on Knowledge capture
EditorsDerek Sleeman, Ken Barker
Place of PublicationNew York, NY (US)
PublisherACM
Pages175-176
Number of pages2
ISBN (Print)978-1-59593-643-1
DOIs
Publication statusPublished - 28 Oct 2007
Event4th International Conference on Knowledge Capture - Whistler, BC, Canada
Duration: 28 Oct 200731 Oct 2007

Conference

Conference4th International Conference on Knowledge Capture
Abbreviated titleK-CAP'07
CountryCanada
CityWhistler, BC
Period28/10/0731/10/07

Fingerprint

Industry

Cite this

Iria, J., Uren, V., Lavelli, A., Blohm, S., Dadzie, A., Franz, T., ... Slavazza, P. (2007). Enhancing enterprise knowledge processes via cross-media extraction. In D. Sleeman, & K. Barker (Eds.), K-CAP '07 - proceedings of the 4th international conference on Knowledge capture (pp. 175-176). New York, NY (US): ACM. https://doi.org/10.1145/1298406.1298441
Iria, Jose ; Uren, Victoria ; Lavelli, Alberto ; Blohm, Sebastian ; Dadzie, Aba-sah ; Franz, Thomas ; Kompatsiaris, Ioannis ; Magalhaes, Joao ; Nikolopoulos, Spiros ; Preisach, Christine ; Slavazza, Piercarlo. / Enhancing enterprise knowledge processes via cross-media extraction. K-CAP '07 - proceedings of the 4th international conference on Knowledge capture. editor / Derek Sleeman ; Ken Barker. New York, NY (US) : ACM, 2007. pp. 175-176
@inproceedings{1d31c001e1f44b63b56ef7e4bc47ce5b,
title = "Enhancing enterprise knowledge processes via cross-media extraction",
abstract = "In large organizations the resources needed to solve challenging problems are typically dispersed over systems within and beyond the organization, and also in different media. However, there is still the need, in knowledge environments, for extraction methods able to combine evidence for a fact from across different media. In many cases the whole is more than the sum of its parts: only when considering the different media simultaneously can enough evidence be obtained to derive facts otherwise inaccessible to the knowledge worker via traditional methods that work on each single medium separately. In this paper, we present a cross-media knowledge extraction framework specifically designed to handle large volumes of documents composed of three types of media text, images and raw data and to exploit the evidence across the media. Our goal is to improve the quality and depth of automatically extracted knowledge.",
author = "Jose Iria and Victoria Uren and Alberto Lavelli and Sebastian Blohm and Aba-sah Dadzie and Thomas Franz and Ioannis Kompatsiaris and Joao Magalhaes and Spiros Nikolopoulos and Christine Preisach and Piercarlo Slavazza",
year = "2007",
month = "10",
day = "28",
doi = "10.1145/1298406.1298441",
language = "English",
isbn = "978-1-59593-643-1",
pages = "175--176",
editor = "Derek Sleeman and Ken Barker",
booktitle = "K-CAP '07 - proceedings of the 4th international conference on Knowledge capture",
publisher = "ACM",
address = "United States",

}

Iria, J, Uren, V, Lavelli, A, Blohm, S, Dadzie, A, Franz, T, Kompatsiaris, I, Magalhaes, J, Nikolopoulos, S, Preisach, C & Slavazza, P 2007, Enhancing enterprise knowledge processes via cross-media extraction. in D Sleeman & K Barker (eds), K-CAP '07 - proceedings of the 4th international conference on Knowledge capture. ACM, New York, NY (US), pp. 175-176, 4th International Conference on Knowledge Capture, Whistler, BC, Canada, 28/10/07. https://doi.org/10.1145/1298406.1298441

Enhancing enterprise knowledge processes via cross-media extraction. / Iria, Jose; Uren, Victoria; Lavelli, Alberto; Blohm, Sebastian; Dadzie, Aba-sah; Franz, Thomas; Kompatsiaris, Ioannis; Magalhaes, Joao; Nikolopoulos, Spiros; Preisach, Christine; Slavazza, Piercarlo.

K-CAP '07 - proceedings of the 4th international conference on Knowledge capture. ed. / Derek Sleeman; Ken Barker. New York, NY (US) : ACM, 2007. p. 175-176.

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

TY - GEN

T1 - Enhancing enterprise knowledge processes via cross-media extraction

AU - Iria, Jose

AU - Uren, Victoria

AU - Lavelli, Alberto

AU - Blohm, Sebastian

AU - Dadzie, Aba-sah

AU - Franz, Thomas

AU - Kompatsiaris, Ioannis

AU - Magalhaes, Joao

AU - Nikolopoulos, Spiros

AU - Preisach, Christine

AU - Slavazza, Piercarlo

PY - 2007/10/28

Y1 - 2007/10/28

N2 - In large organizations the resources needed to solve challenging problems are typically dispersed over systems within and beyond the organization, and also in different media. However, there is still the need, in knowledge environments, for extraction methods able to combine evidence for a fact from across different media. In many cases the whole is more than the sum of its parts: only when considering the different media simultaneously can enough evidence be obtained to derive facts otherwise inaccessible to the knowledge worker via traditional methods that work on each single medium separately. In this paper, we present a cross-media knowledge extraction framework specifically designed to handle large volumes of documents composed of three types of media text, images and raw data and to exploit the evidence across the media. Our goal is to improve the quality and depth of automatically extracted knowledge.

AB - In large organizations the resources needed to solve challenging problems are typically dispersed over systems within and beyond the organization, and also in different media. However, there is still the need, in knowledge environments, for extraction methods able to combine evidence for a fact from across different media. In many cases the whole is more than the sum of its parts: only when considering the different media simultaneously can enough evidence be obtained to derive facts otherwise inaccessible to the knowledge worker via traditional methods that work on each single medium separately. In this paper, we present a cross-media knowledge extraction framework specifically designed to handle large volumes of documents composed of three types of media text, images and raw data and to exploit the evidence across the media. Our goal is to improve the quality and depth of automatically extracted knowledge.

UR - http://dl.acm.org/citation.cfm?doid=1298406.1298441

U2 - 10.1145/1298406.1298441

DO - 10.1145/1298406.1298441

M3 - Conference contribution

SN - 978-1-59593-643-1

SP - 175

EP - 176

BT - K-CAP '07 - proceedings of the 4th international conference on Knowledge capture

A2 - Sleeman, Derek

A2 - Barker, Ken

PB - ACM

CY - New York, NY (US)

ER -

Iria J, Uren V, Lavelli A, Blohm S, Dadzie A, Franz T et al. Enhancing enterprise knowledge processes via cross-media extraction. In Sleeman D, Barker K, editors, K-CAP '07 - proceedings of the 4th international conference on Knowledge capture. New York, NY (US): ACM. 2007. p. 175-176 https://doi.org/10.1145/1298406.1298441