The Constructing of Test Set on Chinese Information Retrieval

Article Preview

Abstract:

In this paper, we propose a Template-Matching strategy combined with statistics in the tasks of human evaluation of NTCIR to avoid the arbitrariness of human evaluators. By practical operation and within-system checkup, the strategy helps avoid the arbitrariness of human evaluators and provides a benchmark for human evaluation of NTCIR.

You might also be interested in these eBooks

Info:

Periodical:

Advanced Materials Research (Volumes 546-547)

Pages:

645-650

Citation:

Online since:

July 2012

Export:

Price:

Permissions CCC:

Permissions PLS:

Сopyright:

© 2012 Trans Tech Publications Ltd. All Rights Reserved

Share:

Citation:

[1] Kando, N., Kuriyama, K., Nozue, T., et al.: Overview of IR Tasks at the First NTCIR Workshop. Proceedings of NTCIR-1 Workshop Meeting, August 30 - September 1, 1999, Tokyo, Japan. 1999: pp.11-34.

DOI: 10.1145/312624.312730

Google Scholar

[2] Kando, N.: Overview of the Seventh NTCIR Workshop. Proceedings of NTCIR-7 Workshop Meeting, December 16–19, 2008, Tokyo, Japan. 2008: pp.1-9.

Google Scholar

[3] Mitamura, T., Nyberg, E., Shima, H., et al.: Overview of the NTCIR-7 ACLIA Tasks: Advanced Cross-Lingual Information Access. Proceedings of NTCIR-7 Workshop Meeting, December 16–19, 2008, Tokyo, Japan. 2008: pp.11-25.

Google Scholar

[4] Sakai, T., Kando, N., Mitamura, T. et al.: Overview of the NTCIR-7 ACLIA IR4QA Subtask. Proceedings of NTCIR-7 Workshop Meeting, December 16–19, 2008, Tokyo, Japan. 2008: pp.1-11.

Google Scholar

[5] Ferro, N., Peters, C.: From CLEF to TrebelCLEF: the Evolution of the Cross-Language Evaluation Forum. Proceedings of NTCIR-7 Workshop Meeting, December 16–19, 2008, Tokyo, Japan. 2008: pp.557-593.

Google Scholar

[6] Harman, D. K.: Overview of the First Text REtrieval Conference (TREC1). The First Text REtrieval Conference (TREC1). Gaithersburg, MD: U.S. Dept. of Commerce, National Institute of Standards and Technology. 1993: pp.1-20.

DOI: 10.6028/nist.sp.500-207

Google Scholar

[7] Deng, Y., Xu, B.J., Liu, S., et al.: Answer Path at NICIR-7 CCLQA Track. Proceedings of NTCIR-7 Workshop Meeting, December 16-19, 2008, Tokyo, Japan. 2008: pp.60-65.

Google Scholar

[8] http: /aclia. lti. cs. cmu. edu: 8080/epan/he/ir_evaluation. jsp.

Google Scholar

[9] http: /wenda. tianya. cn/wenda/thread?tid=0d699255ebc0c8ef.

Google Scholar

[10] Zhang, X. K., Zhao, D.Q.: An Overview on TREC and Its Latest Development. Intelligence Theory and Application. February 16, 2004. Beijing, China. 2004: pp.537-540.

Google Scholar

[11] Zheng, D.Q., Li, S., Zhao, T.J.: CLIR Model Based on a Combination of Ontology and Statistical Method. Journal of Harbin Institute of Technology. January 2008. Harbin, China. 2008: pp.77-80.

Google Scholar

[12] Tang, Y., Lin, L.X., Luo, Y. M. et al.: Survey on Information Retrieval System based on Question Answering System. Computer Applications. November, 2008. Beijing, China. 2008: pp.2745-2748.

DOI: 10.3724/sp.j.1087.2008.02745

Google Scholar

[13] http: /en. www. wikipedia. org.

Google Scholar