Preliminary study of technical terminology for the retrieval of scientific book metadata records

Birger Larsen; Christina Lioma; Ingo Frommholz; Hinrich Schütze

doi:10.1145/2348283.2348504

Preliminary study of technical terminology for the retrieval of scientific book metadata records

Birger Larsen
, Christina Lioma
, Ingo Frommholz
, Hinrich Schütze

Institute for Research in Applicable Computing (IRAC)

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

4 Citations (Scopus)

6 Downloads (Pure)

Abstract

Books only represented by brief metadata (book records) are particularly hard to retrieve. One way of improving their retrieval is by extracting retrieval enhancing features from them. This work focusses on scientific (physics) book records. We ask if their technical terminology can be used as a retrieval enhancing feature. A study of 18,443 book records shows a strong correlation between their technical terminology and their likelihood of relevance. Using this finding for retrieval yields >+5% precision and recall gains.

Original language	English
Title of host publication	nan
Publisher	Association for Computing Machinery
DOIs	https://doi.org/10.1145/2348283.2348504
Publication status	Published - 1 Aug 2012
Event	5th international ACM SIGIR conference on Research and development in information retrieval (SIGIR '12) - Duration: 1 Aug 2012 → …

Conference

Conference	5th international ACM SIGIR conference on Research and development in information retrieval (SIGIR '12)
Period	1/08/12 → …
Other	5th international ACM SIGIR conference on Research and development in information retrieval (SIGIR '12)

Keywords

metadata

Access to Document

10.1145/2348283.2348504

FrommholzAccepted author manuscript, 373 KBLicence: CC BY-NC-ND

https://dl.acm.org/doi/10.1145/2348283.2348504

Handle.net

Persistent link

Cite this

@inproceedings{f8d35f2628ac4b06a2b1e761427f40c8,

title = "Preliminary study of technical terminology for the retrieval of scientific book metadata records",

abstract = "Books only represented by brief metadata (book records) are particularly hard to retrieve. One way of improving their retrieval is by extracting retrieval enhancing features from them. This work focusses on scientific (physics) book records. We ask if their technical terminology can be used as a retrieval enhancing feature. A study of 18,443 book records shows a strong correlation between their technical terminology and their likelihood of relevance. Using this finding for retrieval yields >+5\% precision and recall gains.",

keywords = "metadata",

author = "Birger Larsen and Christina Lioma and Ingo Frommholz and Hinrich Sch{\"u}tze",

year = "2012",

month = aug,

day = "1",

doi = "10.1145/2348283.2348504",

language = "English",

booktitle = "nan",

publisher = "Association for Computing Machinery",

address = "United States",

note = "5th international ACM SIGIR conference on Research and development in information retrieval (SIGIR '12) ; Conference date: 01-08-2012",

}

TY - GEN

T1 - Preliminary study of technical terminology for the retrieval of scientific book metadata records

AU - Larsen, Birger

AU - Lioma, Christina

AU - Frommholz, Ingo

AU - Schütze, Hinrich

PY - 2012/8/1

Y1 - 2012/8/1

N2 - Books only represented by brief metadata (book records) are particularly hard to retrieve. One way of improving their retrieval is by extracting retrieval enhancing features from them. This work focusses on scientific (physics) book records. We ask if their technical terminology can be used as a retrieval enhancing feature. A study of 18,443 book records shows a strong correlation between their technical terminology and their likelihood of relevance. Using this finding for retrieval yields >+5% precision and recall gains.

AB - Books only represented by brief metadata (book records) are particularly hard to retrieve. One way of improving their retrieval is by extracting retrieval enhancing features from them. This work focusses on scientific (physics) book records. We ask if their technical terminology can be used as a retrieval enhancing feature. A study of 18,443 book records shows a strong correlation between their technical terminology and their likelihood of relevance. Using this finding for retrieval yields >+5% precision and recall gains.

KW - metadata

U2 - 10.1145/2348283.2348504

DO - 10.1145/2348283.2348504

M3 - Conference contribution

BT - nan

PB - Association for Computing Machinery

T2 - 5th international ACM SIGIR conference on Research and development in information retrieval (SIGIR '12)

Y2 - 1 August 2012

ER -

Preliminary study of technical terminology for the retrieval of scientific book metadata records

Abstract

Conference

Keywords

Access to Document

Handle.net

Fingerprint

Cite this