LUKe and MIKe: Learning from user knowledge and managing interactive knowledge extraction

Steffen Metzger; Michael Stoll; Katja Hose; Ralf Schenkel

doi:10.1145/2396761.2398721

LUKe and MIKe: Learning from user knowledge and managing interactive knowledge extraction

Steffen Metzger^*, Michael Stoll, Katja Hose, Ralf Schenkel

^*Corresponding author for this work

Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review

Abstract

Semantic recognition and annotation of unqiue enities and their relations is a key in understanding the essence contained in large text corpora. It typically requires a combination of efficient automatic methods and manual verification. Usually, both parts are seen as consecutive steps. In this demo we present MIKE, a user interface enabling the integration of user feedback into an iterative extraction process. We show how an extraction system can directly learn from such integrated user supervision. In general, this setup allows for stepwise training of the extraction system to a particular domain, while using user feedback early in the iterative extraction process improves extraction quality and reduces the overall human effort needed.

Original language	English
Title of host publication	CIKM 2012 - Proceedings of the 21st ACM International Conference on Information and Knowledge Management
Number of pages	3
Publication date	19 Dec 2012
Pages	2671-2673
ISBN (Print)	9781450311564
DOIs	https://doi.org/10.1145/2396761.2398721
Publication status	Published - 19 Dec 2012
Externally published	Yes
Event	21st ACM International Conference on Information and Knowledge Management, CIKM 2012 - Maui, HI, United States Duration: 29 Oct 2012 → 2 Nov 2012

Conference

Conference	21st ACM International Conference on Information and Knowledge Management, CIKM 2012
Country/Territory	United States
City	Maui, HI
Period	29/10/2012 → 02/11/2012
Sponsor	Special Interest Group on Information Retrieval (ACM SIGIR), ACM SIGWEB

Keywords

gui
information extraction
knowledge acquisition
learning
user feedback
web service

Access to Document

10.1145/2396761.2398721

AUB Link

Search for the material in Aalborg University Library's search engine

Cite this

@inproceedings{a6559f73c19e4fa18df75f5b71b30766,

title = "LUKe and MIKe: Learning from user knowledge and managing interactive knowledge extraction",

abstract = "Semantic recognition and annotation of unqiue enities and their relations is a key in understanding the essence contained in large text corpora. It typically requires a combination of efficient automatic methods and manual verification. Usually, both parts are seen as consecutive steps. In this demo we present MIKE, a user interface enabling the integration of user feedback into an iterative extraction process. We show how an extraction system can directly learn from such integrated user supervision. In general, this setup allows for stepwise training of the extraction system to a particular domain, while using user feedback early in the iterative extraction process improves extraction quality and reduces the overall human effort needed.",

keywords = "gui, information extraction, knowledge acquisition, learning, user feedback, web service",

author = "Steffen Metzger and Michael Stoll and Katja Hose and Ralf Schenkel",

year = "2012",

month = dec,

day = "19",

doi = "10.1145/2396761.2398721",

language = "English",

isbn = "9781450311564",

pages = "2671--2673",

booktitle = "CIKM 2012 - Proceedings of the 21st ACM International Conference on Information and Knowledge Management",

note = "21st ACM International Conference on Information and Knowledge Management, CIKM 2012 ; Conference date: 29-10-2012 Through 02-11-2012",

}

Metzger, S, Stoll, M, Hose, K & Schenkel, R 2012, LUKe and MIKe: Learning from user knowledge and managing interactive knowledge extraction. in CIKM 2012 - Proceedings of the 21st ACM International Conference on Information and Knowledge Management. pp. 2671-2673, 21st ACM International Conference on Information and Knowledge Management, CIKM 2012, Maui, HI, United States, 29/10/2012. https://doi.org/10.1145/2396761.2398721

LUKe and MIKe: Learning from user knowledge and managing interactive knowledge extraction. / Metzger, Steffen; Stoll, Michael; Hose, Katja et al.
CIKM 2012 - Proceedings of the 21st ACM International Conference on Information and Knowledge Management. 2012. p. 2671-2673.

Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review

TY - GEN

T1 - LUKe and MIKe

T2 - 21st ACM International Conference on Information and Knowledge Management, CIKM 2012

AU - Metzger, Steffen

AU - Stoll, Michael

AU - Hose, Katja

AU - Schenkel, Ralf

PY - 2012/12/19

Y1 - 2012/12/19

N2 - Semantic recognition and annotation of unqiue enities and their relations is a key in understanding the essence contained in large text corpora. It typically requires a combination of efficient automatic methods and manual verification. Usually, both parts are seen as consecutive steps. In this demo we present MIKE, a user interface enabling the integration of user feedback into an iterative extraction process. We show how an extraction system can directly learn from such integrated user supervision. In general, this setup allows for stepwise training of the extraction system to a particular domain, while using user feedback early in the iterative extraction process improves extraction quality and reduces the overall human effort needed.

AB - Semantic recognition and annotation of unqiue enities and their relations is a key in understanding the essence contained in large text corpora. It typically requires a combination of efficient automatic methods and manual verification. Usually, both parts are seen as consecutive steps. In this demo we present MIKE, a user interface enabling the integration of user feedback into an iterative extraction process. We show how an extraction system can directly learn from such integrated user supervision. In general, this setup allows for stepwise training of the extraction system to a particular domain, while using user feedback early in the iterative extraction process improves extraction quality and reduces the overall human effort needed.

KW - gui

KW - information extraction

KW - knowledge acquisition

KW - learning

KW - user feedback

KW - web service

UR - http://www.scopus.com/inward/record.url?scp=84871046710&partnerID=8YFLogxK

U2 - 10.1145/2396761.2398721

DO - 10.1145/2396761.2398721

M3 - Article in proceeding

AN - SCOPUS:84871046710

SN - 9781450311564

SP - 2671

EP - 2673

BT - CIKM 2012 - Proceedings of the 21st ACM International Conference on Information and Knowledge Management

Y2 - 29 October 2012 through 2 November 2012

ER -

LUKe and MIKe: Learning from user knowledge and managing interactive knowledge extraction

Abstract

Conference

Keywords

Access to Document

AUB Link

Other files and links

Fingerprint

Cite this