MetaExtract: An NLP system to automatically assign metadata

Ozgur Yilmazel; Christina M. Finneran; Elizabeth D. Liddy

MetaExtract: An NLP system to automatically assign metadata

Ozgur Yilmazel, Christina M. Finneran, Elizabeth D. Liddy

School of Information Studies

Research output: Chapter in Book/Entry/Poem › Conference contribution

36 Scopus citations

Abstract

We have developed MetaExtract, a system to automatically assign Dublin Core + GEM metadata using extraction techniques from our natural language processing research. MetaExtract is comprised of three distinct processes: eQuery and HTML-based Extraction modules and a Keyword Generator module. We conducted a Web-based survey to have users evaluate each metadata element's quality. Only two of the elements, Title and Keyword, were shown to be significantly different, with the manual quality slightly higher. The remaining elements for which we had enough data to test were shown not to be significantly different; they are: Description, Grade, Duration, Essential Resources, Pedagogy-Teaching Method, and Pedagogy-Group.

Original language	English (US)
Title of host publication	Proceedings of the Fourth ACM/IEEE Joint Conference on Digital Libraries; Global Reach and Diverse Impact, JCDL 2004
Editors	H. Chen, M. Christel, E.P. Lim
Pages	241-242
Number of pages	2
State	Published - 2004
Event	Proceedings of the Fourth ACM/IEEE Joint Conference on Digital Libraries; Global reach and Diverse Impact, JCDL 2004 - Tucson, AZ, United States Duration: Jun 7 2004 → Jun 11 2004

Publication series

Name	Proceedings of the ACM IEEE International Conference on Digital Libraries, JCDL 2004

Other

Other	Proceedings of the Fourth ACM/IEEE Joint Conference on Digital Libraries; Global reach and Diverse Impact, JCDL 2004
Country/Territory	United States
City	Tucson, AZ
Period	6/7/04 → 6/11/04

Keywords

Design
Measurement

ASJC Scopus subject areas

Software
Information Systems
Computer Science Applications
Library and Information Sciences

Cite this

Yilmazel, O., Finneran, C. M., & Liddy, E. D. (2004). MetaExtract: An NLP system to automatically assign metadata. In H. Chen, M. Christel, & E. P. Lim (Eds.), Proceedings of the Fourth ACM/IEEE Joint Conference on Digital Libraries; Global Reach and Diverse Impact, JCDL 2004 (pp. 241-242). (Proceedings of the ACM IEEE International Conference on Digital Libraries, JCDL 2004).

MetaExtract: An NLP system to automatically assign metadata. / Yilmazel, Ozgur; Finneran, Christina M.; Liddy, Elizabeth D.
Proceedings of the Fourth ACM/IEEE Joint Conference on Digital Libraries; Global Reach and Diverse Impact, JCDL 2004. ed. / H. Chen; M. Christel; E.P. Lim. 2004. p. 241-242 (Proceedings of the ACM IEEE International Conference on Digital Libraries, JCDL 2004).

Research output: Chapter in Book/Entry/Poem › Conference contribution

Yilmazel, O, Finneran, CM & Liddy, ED 2004, MetaExtract: An NLP system to automatically assign metadata. in H Chen, M Christel & EP Lim (eds), Proceedings of the Fourth ACM/IEEE Joint Conference on Digital Libraries; Global Reach and Diverse Impact, JCDL 2004. Proceedings of the ACM IEEE International Conference on Digital Libraries, JCDL 2004, pp. 241-242, Proceedings of the Fourth ACM/IEEE Joint Conference on Digital Libraries; Global reach and Diverse Impact, JCDL 2004, Tucson, AZ, United States, 6/7/04.

Yilmazel, Ozgur ; Finneran, Christina M. ; Liddy, Elizabeth D. / MetaExtract : An NLP system to automatically assign metadata. Proceedings of the Fourth ACM/IEEE Joint Conference on Digital Libraries; Global Reach and Diverse Impact, JCDL 2004. editor / H. Chen ; M. Christel ; E.P. Lim. 2004. pp. 241-242 (Proceedings of the ACM IEEE International Conference on Digital Libraries, JCDL 2004).

@inproceedings{8243e40fdcc74aa2b491b381e3b01af5,

title = "MetaExtract: An NLP system to automatically assign metadata",

abstract = "We have developed MetaExtract, a system to automatically assign Dublin Core + GEM metadata using extraction techniques from our natural language processing research. MetaExtract is comprised of three distinct processes: eQuery and HTML-based Extraction modules and a Keyword Generator module. We conducted a Web-based survey to have users evaluate each metadata element's quality. Only two of the elements, Title and Keyword, were shown to be significantly different, with the manual quality slightly higher. The remaining elements for which we had enough data to test were shown not to be significantly different; they are: Description, Grade, Duration, Essential Resources, Pedagogy-Teaching Method, and Pedagogy-Group.",

keywords = "Design, Measurement",

author = "Ozgur Yilmazel and Finneran, {Christina M.} and Liddy, {Elizabeth D.}",

year = "2004",

language = "English (US)",

isbn = "1581138326",

series = "Proceedings of the ACM IEEE International Conference on Digital Libraries, JCDL 2004",

pages = "241--242",

editor = "H. Chen and M. Christel and E.P. Lim",

booktitle = "Proceedings of the Fourth ACM/IEEE Joint Conference on Digital Libraries; Global Reach and Diverse Impact, JCDL 2004",

note = "Proceedings of the Fourth ACM/IEEE Joint Conference on Digital Libraries; Global reach and Diverse Impact, JCDL 2004 ; Conference date: 07-06-2004 Through 11-06-2004",

}

TY - GEN

T1 - MetaExtract

T2 - Proceedings of the Fourth ACM/IEEE Joint Conference on Digital Libraries; Global reach and Diverse Impact, JCDL 2004

AU - Yilmazel, Ozgur

AU - Finneran, Christina M.

AU - Liddy, Elizabeth D.

PY - 2004

Y1 - 2004

N2 - We have developed MetaExtract, a system to automatically assign Dublin Core + GEM metadata using extraction techniques from our natural language processing research. MetaExtract is comprised of three distinct processes: eQuery and HTML-based Extraction modules and a Keyword Generator module. We conducted a Web-based survey to have users evaluate each metadata element's quality. Only two of the elements, Title and Keyword, were shown to be significantly different, with the manual quality slightly higher. The remaining elements for which we had enough data to test were shown not to be significantly different; they are: Description, Grade, Duration, Essential Resources, Pedagogy-Teaching Method, and Pedagogy-Group.

AB - We have developed MetaExtract, a system to automatically assign Dublin Core + GEM metadata using extraction techniques from our natural language processing research. MetaExtract is comprised of three distinct processes: eQuery and HTML-based Extraction modules and a Keyword Generator module. We conducted a Web-based survey to have users evaluate each metadata element's quality. Only two of the elements, Title and Keyword, were shown to be significantly different, with the manual quality slightly higher. The remaining elements for which we had enough data to test were shown not to be significantly different; they are: Description, Grade, Duration, Essential Resources, Pedagogy-Teaching Method, and Pedagogy-Group.

KW - Design

KW - Measurement

UR - http://www.scopus.com/inward/record.url?scp=4944255256&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=4944255256&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:4944255256

SN - 1581138326

SN - 9781581138320

T3 - Proceedings of the ACM IEEE International Conference on Digital Libraries, JCDL 2004

SP - 241

EP - 242

BT - Proceedings of the Fourth ACM/IEEE Joint Conference on Digital Libraries; Global Reach and Diverse Impact, JCDL 2004

A2 - Chen, H.

A2 - Christel, M.

A2 - Lim, E.P.

Y2 - 7 June 2004 through 11 June 2004

ER -

MetaExtract: An NLP system to automatically assign metadata

Abstract

Publication series

Other

Keywords

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this