Advances in Information Retrieval Theory: Third by ChengXiang Zhai (auth.), Giambattista Amati, Fabio Crestani

By ChengXiang Zhai (auth.), Giambattista Amati, Fabio Crestani (eds.)

This e-book constitutes the refereed lawsuits of the 3rd foreign convention at the concept of knowledge Retrieval, ICTIR 2011, held in Bertinoro, Italy, in September 2011. The 25 revised complete papers and thirteen brief papers awarded including the abstracts of 2 invited talks have been conscientiously reviewed and chosen from sixty five submissions. The papers conceal issues starting from question enlargement, co-occurence research, consumer and interactive modelling, method functionality prediction and comparability, and probabilistic ways for score and modelling IR to issues with regards to interdisciplinary methods or purposes. they're equipped into the subsequent topical sections: predicting question functionality; latent semantic research and observe co-occurrence research; question enlargement and re-ranking; comparability of knowledge retrieval platforms and approximate seek; likelihood rating precept and choices; interdisciplinary ways; consumer and relevance; end result diversification and question disambiguation; and logical operators and descriptive approaches.

Show description

Read Online or Download Advances in Information Retrieval Theory: Third International Conference, ICTIR 2011, Bertinoro, Italy, September 12-14, 2011. Proceedings PDF

Similar international books

Agents and Artificial Intelligence: Second International Conference, ICAART 2010, Valencia, Spain, January 22-24, 2010. Revised Selected Papers

This ebook constitutes the completely refereed post-conference complaints of the second one foreign convention on brokers and synthetic Intelligence, ICAART 2010, held in Valencia, Spain, in January 2010. The 17 revised complete papers provided including an invited paper have been conscientiously reviewed and chosen from 364 submissions.

The Semantic Web – ISWC 2010: 9th International Semantic Web Conference, ISWC 2010, Shanghai, China, November 7-11, 2010, Revised Selected Papers, Part II

The two-volume set LNCS 6496 and 6497 constitutes the refereed complaints of the ninth overseas Semantic internet convention, ISWC 2010, held in Shanghai, China, in the course of November 7-11, 2010. half I includes fifty one papers out of 578 submissions to the study song. half II comprises 18 papers out of sixty six submissions to the semantic internet in-use song, 6 papers out of 26 submissions to the doctoral consortium music, and in addition four invited talks.

Temporal Disorder in Human Oscillatory Systems: Proceedings of an International Symposium University of Bremen, 8–13 September 1986

Rhythms of the center and of the frightened and endocrine procedure, respiring, locomotory routine, sleep, circadian rhythms and tissue mobilephone cycles are significant components of the temporal order of guy. The dynamics of those platforms are characterised through adjustments within the homes of an oscillator, transitions from oscillatory states into chaotic or desk bound states, and vice versa, coupling or uncoupling among or extra oscillators.

Extra resources for Advances in Information Retrieval Theory: Third International Conference, ICTIR 2011, Bertinoro, Italy, September 12-14, 2011. Proceedings

Example text

Taking inspiration in the query performance predictor known as query clarity, we have defined and elaborated in the Recommender Systems domain several predictive models according to different formulations and assumptions. We obtain strong correlation values confirming that our approach results in a high predictive power for recommender systems performance. As a side-effect, our study introduces an interesting revision of the gray sheep user concept. A simplistic interpretation of the gray sheep intuition would suggest that users with a too unusual behavior are a difficult target for recommendations.

1. Using a relevance model, RRel , constructed from r (≥ 1) relevant documents in QF; for r = 0, the (pseudo feedback) result-list-based relevance model, RRes , is used. The left figure presents the MAP performance of using the relevance model for retrieval over the corpus. ) The right figure presents QF’s resultant prediction quality. can be attained by using an estimate of the “optimal” ranking as a reference comparison in estimating the effectiveness of the given ranking. Using Both Effective and Ineffective Rankings.

A ‘5’) is larger for user 2 than for user 1, and at the same time, the most popular rating value (a ‘4’) is much more likely for user 1. The figure about the ItemUser model is less clear in this aspect, although two big spikes are observed for user 1 with respect to the collection distribution, which correspond with two strange movies: ‘Waiting for Guffman’ and ‘Cry, the beloved country’, both with a very low collection probability. Finally, the figure about the IRUserItem model successfully shows how user 2 has more spikes than user 1, indicating a clear divergence from the backgrund model; in fact, user 1’s distribution partially mimics that of the collection.

Download PDF sample

Rated 4.81 of 5 – based on 43 votes