Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

16

CIKM
2011
Springer

favoriteEmaildiscussreport

239views Information Technology» more CIKM 2011»

Adaptive term frequency normalization for BM25

12 years 4 months ago

Adaptive term frequency normalization for BM25

Download sifaka.cs.uiuc.edu

A key component of BM25 contributing to its success is its sub-linear term frequency (TF) normalization formula. The scale and shape of this TF normalization component is controlled by a parameter k1, which is generally set to a term-independent constant. We hypothesize and show empirically that in order to optimize retrieval performance, this parameter should be set in a term-speciﬁc way. Following this intuition, we propose an information gain measure to directly estimate the contributions of repeated term occurrences, which is then exploited to ﬁt the BM25 function to

Yuanhua Lv, ChengXiang Zhai

Real-time Traffic

CIKM 2011 | Information Gain | Information Technology | Retrieval Performance | Term Occurrences |

claim paper

Related Content

» When documents are very long BM25 fails

» Lowerbounding term frequency normalization

» The Hong Kong Polytechnic University at the TREC 2004 Robust Track

» A Bayesian Approach for Learning Document Type Relevance

» Frequencyaware rate adaptation and MAC protocols

» ImageQualityBased Adaptive Face Recognition

» TextIndependent Speaker Authentication with Spiking Neural Networks

» TransmitterBased PreProcessing for OFDMCDMA ForwardLink Systems with TwoDimensional Spread...

» Feature Detection with Automatic Scale Selection

Post Info
More Details (n/a)

Added	13 Dec 2011
Updated	13 Dec 2011
Type	Journal
Year	2011
Where	CIKM
Authors	Yuanhua Lv, ChengXiang Zhai

Comments (0)