Utilizing images for assisting cross-language information retrieval on the Web

Yoshihiko Hayashi, Savas Ali Bora, Masaaki Nagata

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

4 Citations (Scopus)

Abstract

In this paper, we discuss the effectiveness of employing visual clues in interactive cross-language information retrieval o assist users in selecting appropriate translation candidates for a query term. Experimental results show that by associating images collected by a Web image search, for each translation candidate, the selection of correct translations was considerably improved (by 29.3%) and the efficiency of the selection was enhanced, i.e., the elapsed time in selection was substantially reduced (by 16.7%) compared to the cases where only back-translated terms were presented. The results suggest that visual items, even if simply collected by a Web image search without any image sense disambiguation, can be superior to verbal information as clues for query term selection in target languages that the user is not familiar with.

Original languageEnglish
Title of host publicationProceedings - 2009 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology - Workshops, WI-IAT Workshops 2009
Pages100-103
Number of pages4
Volume3
DOIs
Publication statusPublished - 2009
Externally publishedYes
Event2009 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology - Workshops, WI-IAT Workshops 2009 - Milano, Italy
Duration: 2009 Sep 152009 Sep 18

Other

Other2009 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology - Workshops, WI-IAT Workshops 2009
CountryItaly
CityMilano
Period09/9/1509/9/18

Fingerprint

Query languages

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Software

Cite this

Hayashi, Y., Bora, S. A., & Nagata, M. (2009). Utilizing images for assisting cross-language information retrieval on the Web. In Proceedings - 2009 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology - Workshops, WI-IAT Workshops 2009 (Vol. 3, pp. 100-103). [5286004] https://doi.org/10.1109/WI-IAT.2009.240

Utilizing images for assisting cross-language information retrieval on the Web. / Hayashi, Yoshihiko; Bora, Savas Ali; Nagata, Masaaki.

Proceedings - 2009 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology - Workshops, WI-IAT Workshops 2009. Vol. 3 2009. p. 100-103 5286004.

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

Hayashi, Y, Bora, SA & Nagata, M 2009, Utilizing images for assisting cross-language information retrieval on the Web. in Proceedings - 2009 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology - Workshops, WI-IAT Workshops 2009. vol. 3, 5286004, pp. 100-103, 2009 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology - Workshops, WI-IAT Workshops 2009, Milano, Italy, 09/9/15. https://doi.org/10.1109/WI-IAT.2009.240
Hayashi Y, Bora SA, Nagata M. Utilizing images for assisting cross-language information retrieval on the Web. In Proceedings - 2009 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology - Workshops, WI-IAT Workshops 2009. Vol. 3. 2009. p. 100-103. 5286004 https://doi.org/10.1109/WI-IAT.2009.240
Hayashi, Yoshihiko ; Bora, Savas Ali ; Nagata, Masaaki. / Utilizing images for assisting cross-language information retrieval on the Web. Proceedings - 2009 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology - Workshops, WI-IAT Workshops 2009. Vol. 3 2009. pp. 100-103
@inproceedings{6a3ae2f60baf465ab7aecb7521544791,
title = "Utilizing images for assisting cross-language information retrieval on the Web",
abstract = "In this paper, we discuss the effectiveness of employing visual clues in interactive cross-language information retrieval o assist users in selecting appropriate translation candidates for a query term. Experimental results show that by associating images collected by a Web image search, for each translation candidate, the selection of correct translations was considerably improved (by 29.3{\%}) and the efficiency of the selection was enhanced, i.e., the elapsed time in selection was substantially reduced (by 16.7{\%}) compared to the cases where only back-translated terms were presented. The results suggest that visual items, even if simply collected by a Web image search without any image sense disambiguation, can be superior to verbal information as clues for query term selection in target languages that the user is not familiar with.",
author = "Yoshihiko Hayashi and Bora, {Savas Ali} and Masaaki Nagata",
year = "2009",
doi = "10.1109/WI-IAT.2009.240",
language = "English",
isbn = "9780769538013",
volume = "3",
pages = "100--103",
booktitle = "Proceedings - 2009 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology - Workshops, WI-IAT Workshops 2009",

}

TY - GEN

T1 - Utilizing images for assisting cross-language information retrieval on the Web

AU - Hayashi, Yoshihiko

AU - Bora, Savas Ali

AU - Nagata, Masaaki

PY - 2009

Y1 - 2009

N2 - In this paper, we discuss the effectiveness of employing visual clues in interactive cross-language information retrieval o assist users in selecting appropriate translation candidates for a query term. Experimental results show that by associating images collected by a Web image search, for each translation candidate, the selection of correct translations was considerably improved (by 29.3%) and the efficiency of the selection was enhanced, i.e., the elapsed time in selection was substantially reduced (by 16.7%) compared to the cases where only back-translated terms were presented. The results suggest that visual items, even if simply collected by a Web image search without any image sense disambiguation, can be superior to verbal information as clues for query term selection in target languages that the user is not familiar with.

AB - In this paper, we discuss the effectiveness of employing visual clues in interactive cross-language information retrieval o assist users in selecting appropriate translation candidates for a query term. Experimental results show that by associating images collected by a Web image search, for each translation candidate, the selection of correct translations was considerably improved (by 29.3%) and the efficiency of the selection was enhanced, i.e., the elapsed time in selection was substantially reduced (by 16.7%) compared to the cases where only back-translated terms were presented. The results suggest that visual items, even if simply collected by a Web image search without any image sense disambiguation, can be superior to verbal information as clues for query term selection in target languages that the user is not familiar with.

UR - http://www.scopus.com/inward/record.url?scp=84856936937&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84856936937&partnerID=8YFLogxK

U2 - 10.1109/WI-IAT.2009.240

DO - 10.1109/WI-IAT.2009.240

M3 - Conference contribution

AN - SCOPUS:84856936937

SN - 9780769538013

VL - 3

SP - 100

EP - 103

BT - Proceedings - 2009 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology - Workshops, WI-IAT Workshops 2009

ER -