Advances in Information Retrieval: 31th European Conference - download pdf or read online

By W. Bruce Croft (auth.), Mohand Boughanem, Catherine Berrut, Josiane Mothe, Chantal Soule-Dupuy (eds.)

ISBN-10: 3642009573

ISBN-13: 9783642009570

ISBN-10: 3642009581

ISBN-13: 9783642009587

This e-book constitutes the refereed court cases of the thirtieth annual ecu convention on details Retrieval study, ECIR 2009, held in Toulouse, France in April 2009.

The forty two revised complete papers and 18 revised brief papers provided including the abstracts of three invited lectures and 25 poster papers have been conscientiously reviewed and chosen from 188 submissions. The papers are equipped in topical sections on retrieval version, collaborative IR / filtering, studying, multimedia - metadata, specialist seek - ads, overview, opinion detection, internet IR, illustration, clustering / categorization in addition to dispensed IR.

Show description

Read or Download Advances in Information Retrieval: 31th European Conference on IR Research, ECIR 2009, Toulouse, France, April 6-9, 2009. Proceedings PDF

Best european books

Download PDF by G. Christou: The European Union and Enlargement: The Case of Cyprus

Given the present unrest within the center East, this ebook evaluates the power of the ecu Union via growth to avoid a possible clash constructing among key actors within the near-eastern Mediterranean quarter; specifically Greece, Turkey and Cyprus. Cyprus and the Cyprus factor becomes more and more vital within the following few years given the final touch of accession negotiations, and the signing of the Accession Treaty in April 2003 among Cyprus and the eu Union.

Get Invited Lectures. Proceedings of the Third Congress of the PDF

Exogenous and Endogenous affects on Metabolic and Neural keep an eye on, quantity 1: Invited Lectures covers the court cases of the 3rd Congress of the ecu Society for Comparative body structure and Biochemistry. The publication provides 35 papers that hide a number of facets within the keep watch over of physiological actions in animals.

Download e-book for iPad: Marine Phytoplankton and Productivity: Proceedings of the by O. Holm-Hansen, L. Bolis, R. Gilles

While i used to be requested to arrange this symposium on marine producti­ vity, it made me give some thought to what points of this topic will be stimulating to a heterogeneous team of laboratory-oriented physiolo­ gists and biochemists. lately there were numerous books which discusses the method regular in fundamental construction reports and defined the significance of photosynthetic CO aid 2 in a number of components of the world's oceans.

Extra info for Advances in Information Retrieval: 31th European Conference on IR Research, ECIR 2009, Toulouse, France, April 6-9, 2009. Proceedings

Example text

The exact reason for the variation between MRR and MAP will be the subject of future work. We next compare to models using background smoothing. Fig. 1 (c) shows the performance gain on MRR for both Jelinek-Mercer and Dirichlet smoothing with different parameters for the TREC8 collection. We can see from Fig. 1 (c) that a risk-aversion approach is effective for all five different background smoothing methods. However, increasing the influence of background smoothing via large values of λ or μ reduces the effectiveness of risk adjustment.

1) follows previous work on considering both the probability of relevance and non-relevance in document ranking [4,10]. The logit model favours documents that are highly relevant for some terms in a multi-term query2 . The estimated mean and variance of the normal distribution obtained from Eq. (1) are given by E[f (θt )] ≈ ln θ¯t 2θ¯t − 1 + ¯2 V ar(θt ) ¯ 1 − θt 2θt (1 − θ¯t )2 V ar(θt ) , V ar[f (θt )] ≈ ¯2 θt (1 − θ¯t )2 (2) (3) where the mean and variance of θt are θ¯t and V ar(θt ), respectively, E[f (θt )] is the mean of f (θt ), and V ar[f (θt )] is the variance of f (θt ).

9 out of 24 results are statistically significant, 22 out of 24 improvements are positive, and the highest improvement on MRR is over 25%, showing that risk adjustment can dramatically increase the chance of returning one relevant document close to the top of a ranked list. Our approach also outperforms the linear smoothing approach on MAP for all four collections. Comparing Table 3 (b) with Table 3 (a), we can see that our approach combined with the linear smoothing performs better than our approach without background smoothing in 18 out of 24 results, and better than the Dirichlet smoothing in 18 out of 24 results.

Download PDF sample

Advances in Information Retrieval: 31th European Conference on IR Research, ECIR 2009, Toulouse, France, April 6-9, 2009. Proceedings by W. Bruce Croft (auth.), Mohand Boughanem, Catherine Berrut, Josiane Mothe, Chantal Soule-Dupuy (eds.)


by Edward
4.4

Rated 4.06 of 5 – based on 7 votes