Post-Modern Portfolio Theory for Information Retrieval

uTaipei > College of Science > Department of Computer Science > Periodical Articles > Item 987654321/16972

Please use this identifier to cite or link to this item: http://utaipeir.lib.utaipei.edu.tw/dspace/handle/987654321/16972

Title:	Post-Modern Portfolio Theory for Information Retrieval
Authors:	Tsai, Ming-Feng;Wang, Chuan-Ju;王釧茹
Contributors:	臺北市立教育大學資訊科學系
Keywords:	Retrieval models;Optimization;Semivariance
Date:	2012
Issue Date:	2019-02-14
Abstract:	Information Retrieval (IR) aims to discover relevant information according to a user's information need. The classic Probability Ranking Principle (PRP) forms the theoretical basis for probabilistic IR models. This ranking principle, however, neglects the uncertainty introduced through the estimations from retrieval models. Inspired by the Post-Modern Portfolio Theory (PMPT), this paper proposes a mean-semivariance framework to handle the uncertainty. The proposed framework not only deals with the uncertainty but has the ability to distinguish bad surprises (downside uncertainty) and good surprises (upside uncertainty) when optimizing a ranking list. The experimental results shows that the proposed method improves the IR performance over the PRP baseline in terms of most of IR evaluation metrics; moreover, the results suggest that the mean-semivariance framework can further boost the top-position ranking quality.
Relation:	Procedia Computer Science，Vol. 13，P.80-85
Appears in Collections:	[Department of Computer Science] Periodical Articles

Files in This Item:

There are no files associated with this item.