Evaluating Score Normalization Methods in Data Fusion

Shengli Wu; Fabio Crestani; Yaxin Bi

Evaluating Score Normalization Methods in Data Fusion

Shengli Wu
, Fabio Crestani
, Yaxin Bi

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

Abstract

In data fusion, score normalization is a step to make scores, which are obtained from different component systems for all documents, comparable to each other. It is an indispensable step for effective data fusion algorithms such as CombSum and CombMNZ to combine them. In this paper, we evaluate four linear score normalization methods, namely the fitting method, Zero-one, Sum, and ZMUV, through extensive experiments. The experimental results show that the fitting method and Zero-one appear to be the two leading methods.

Original language	English
Title of host publication	Unknown Host Publication
Publisher	Springer
Number of pages	6
Publication status	Published (in print/issue) - 2006
Event	AIRS'06 Proceedings of the Third Asia conference on Information Retrieval Technology - Duration: 1 Jan 2006 → …

Conference

Conference	AIRS'06 Proceedings of the Third Asia conference on Information Retrieval Technology
Period	1/01/06 → …

Cite this

@inproceedings{d1aff2f483bf4978a35742dc52f45301,

title = "Evaluating Score Normalization Methods in Data Fusion",

abstract = "In data fusion, score normalization is a step to make scores, which are obtained from different component systems for all documents, comparable to each other. It is an indispensable step for effective data fusion algorithms such as CombSum and CombMNZ to combine them. In this paper, we evaluate four linear score normalization methods, namely the fitting method, Zero-one, Sum, and ZMUV, through extensive experiments. The experimental results show that the fitting method and Zero-one appear to be the two leading methods.",

author = "Shengli Wu and Fabio Crestani and Yaxin Bi",

year = "2006",

language = "English",

booktitle = "Unknown Host Publication",

publisher = "Springer",

address = "Switzerland",

note = "AIRS'06 Proceedings of the Third Asia conference on Information Retrieval Technology ; Conference date: 01-01-2006",

}

TY - GEN

T1 - Evaluating Score Normalization Methods in Data Fusion

AU - Wu, Shengli

AU - Crestani, Fabio

AU - Bi, Yaxin

PY - 2006

Y1 - 2006

N2 - In data fusion, score normalization is a step to make scores, which are obtained from different component systems for all documents, comparable to each other. It is an indispensable step for effective data fusion algorithms such as CombSum and CombMNZ to combine them. In this paper, we evaluate four linear score normalization methods, namely the fitting method, Zero-one, Sum, and ZMUV, through extensive experiments. The experimental results show that the fitting method and Zero-one appear to be the two leading methods.

AB - In data fusion, score normalization is a step to make scores, which are obtained from different component systems for all documents, comparable to each other. It is an indispensable step for effective data fusion algorithms such as CombSum and CombMNZ to combine them. In this paper, we evaluate four linear score normalization methods, namely the fitting method, Zero-one, Sum, and ZMUV, through extensive experiments. The experimental results show that the fitting method and Zero-one appear to be the two leading methods.

M3 - Conference contribution

BT - Unknown Host Publication

PB - Springer

T2 - AIRS'06 Proceedings of the Third Asia conference on Information Retrieval Technology

Y2 - 1 January 2006

ER -

Evaluating Score Normalization Methods in Data Fusion

Abstract

Conference

Fingerprint

Cite this