A figure search engine architecture for a chemistry digital library

Sagnik Ray Choudhury; Suppawong Tuarob; Prasenjit Mitra; Lior Rokach; Andi Kirk; Silvia Szep; Donald Pellegrino; Sue Jones; C. Lee Giles

doi:10.1145/2467696.2467757

A figure search engine architecture for a chemistry digital library

Sagnik Ray Choudhury
, Suppawong Tuarob
, Prasenjit Mitra
, Lior Rokach
, Andi Kirk
, Silvia Szep
, Donald Pellegrino
, Sue Jones
, C. Lee Giles

Pennsylvania State University
Faculty of Health Sciences of the Ben-Gurion University of the Negev
Dow Chemical Company

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

31 Citations (Scopus)

Abstract

Academic papers contain multiple figures representing important findings and experimental results; we present a search engine specifically focused on figures in academic documents. This search engine allows users to search on figures in approximately 150,000 chemistry journal articles though the method is easily extendable to other domains. Our system indexes figure caption and mentions extracted from the PDF in documents using a custom built extractor. Recall and precision performance of extracted figures is in the 80 to 90 % range. We give the frame work for the extraction algorithm, architecture and ranking function.

Original language	English
Title of host publication	JCDL 2013 - Proceedings of the 13th ACM/IEEE-CS Joint Conference on Digital Libraries
Pages	369-370
Number of pages	2
DOIs	https://doi.org/10.1145/2467696.2467757
Publication status	Published - 2013
Externally published	Yes
Event	13th ACM/IEEE-CS Joint Conference on Digital Libraries, JCDL 2013 - Indianapolis, IN, United States Duration: 22 Jul 2013 → 26 Jul 2013

Publication series

Name	Proceedings of the ACM/IEEE Joint Conference on Digital Libraries
ISSN (Print)	1552-5996

Conference

Conference	13th ACM/IEEE-CS Joint Conference on Digital Libraries, JCDL 2013
Country/Territory	United States
City	Indianapolis, IN
Period	22/07/13 → 26/07/13

Keywords

Figure search
Information extraction

Access to Document

10.1145/2467696.2467757

Cite this

Choudhury, S. R., Tuarob, S., Mitra, P., Rokach, L., Kirk, A., Szep, S., Pellegrino, D., Jones, S., & Lee Giles, C. (2013). A figure search engine architecture for a chemistry digital library. In JCDL 2013 - Proceedings of the 13th ACM/IEEE-CS Joint Conference on Digital Libraries (pp. 369-370). (Proceedings of the ACM/IEEE Joint Conference on Digital Libraries). https://doi.org/10.1145/2467696.2467757

@inproceedings{fdf97fbe387c46a5b24d94d793436e4d,

title = "A figure search engine architecture for a chemistry digital library",

abstract = "Academic papers contain multiple figures representing important findings and experimental results; we present a search engine specifically focused on figures in academic documents. This search engine allows users to search on figures in approximately 150,000 chemistry journal articles though the method is easily extendable to other domains. Our system indexes figure caption and mentions extracted from the PDF in documents using a custom built extractor. Recall and precision performance of extracted figures is in the 80 to 90 \% range. We give the frame work for the extraction algorithm, architecture and ranking function.",

keywords = "Figure search, Information extraction",

author = "Choudhury, \{Sagnik Ray\} and Suppawong Tuarob and Prasenjit Mitra and Lior Rokach and Andi Kirk and Silvia Szep and Donald Pellegrino and Sue Jones and \{Lee Giles\}, C.",

year = "2013",

doi = "10.1145/2467696.2467757",

language = "English",

isbn = "9781450320764",

series = "Proceedings of the ACM/IEEE Joint Conference on Digital Libraries",

pages = "369--370",

booktitle = "JCDL 2013 - Proceedings of the 13th ACM/IEEE-CS Joint Conference on Digital Libraries",

note = "13th ACM/IEEE-CS Joint Conference on Digital Libraries, JCDL 2013 ; Conference date: 22-07-2013 Through 26-07-2013",

}

Choudhury, SR, Tuarob, S, Mitra, P, Rokach, L, Kirk, A, Szep, S, Pellegrino, D, Jones, S & Lee Giles, C 2013, A figure search engine architecture for a chemistry digital library. in JCDL 2013 - Proceedings of the 13th ACM/IEEE-CS Joint Conference on Digital Libraries. Proceedings of the ACM/IEEE Joint Conference on Digital Libraries, pp. 369-370, 13th ACM/IEEE-CS Joint Conference on Digital Libraries, JCDL 2013, Indianapolis, IN, United States, 22/07/13. https://doi.org/10.1145/2467696.2467757

A figure search engine architecture for a chemistry digital library. / Choudhury, Sagnik Ray; Tuarob, Suppawong; Mitra, Prasenjit et al.
JCDL 2013 - Proceedings of the 13th ACM/IEEE-CS Joint Conference on Digital Libraries. 2013. p. 369-370 (Proceedings of the ACM/IEEE Joint Conference on Digital Libraries).

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

TY - GEN

T1 - A figure search engine architecture for a chemistry digital library

AU - Choudhury, Sagnik Ray

AU - Tuarob, Suppawong

AU - Mitra, Prasenjit

AU - Rokach, Lior

AU - Kirk, Andi

AU - Szep, Silvia

AU - Pellegrino, Donald

AU - Jones, Sue

AU - Lee Giles, C.

PY - 2013

Y1 - 2013

N2 - Academic papers contain multiple figures representing important findings and experimental results; we present a search engine specifically focused on figures in academic documents. This search engine allows users to search on figures in approximately 150,000 chemistry journal articles though the method is easily extendable to other domains. Our system indexes figure caption and mentions extracted from the PDF in documents using a custom built extractor. Recall and precision performance of extracted figures is in the 80 to 90 % range. We give the frame work for the extraction algorithm, architecture and ranking function.

AB - Academic papers contain multiple figures representing important findings and experimental results; we present a search engine specifically focused on figures in academic documents. This search engine allows users to search on figures in approximately 150,000 chemistry journal articles though the method is easily extendable to other domains. Our system indexes figure caption and mentions extracted from the PDF in documents using a custom built extractor. Recall and precision performance of extracted figures is in the 80 to 90 % range. We give the frame work for the extraction algorithm, architecture and ranking function.

KW - Figure search

KW - Information extraction

UR - https://www.scopus.com/pages/publications/84882283062

U2 - 10.1145/2467696.2467757

DO - 10.1145/2467696.2467757

M3 - Conference contribution

AN - SCOPUS:84882283062

SN - 9781450320764

T3 - Proceedings of the ACM/IEEE Joint Conference on Digital Libraries

SP - 369

EP - 370

BT - JCDL 2013 - Proceedings of the 13th ACM/IEEE-CS Joint Conference on Digital Libraries

T2 - 13th ACM/IEEE-CS Joint Conference on Digital Libraries, JCDL 2013

Y2 - 22 July 2013 through 26 July 2013

ER -

A figure search engine architecture for a chemistry digital library

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this