Filters








84,195 Hits in 3.4 sec

A Topical Approach to Retrievability Bias Estimation

Colin Wilkie, Leif Azzopardi
2016 Proceedings of the 2016 ACM International Conference on the Theory of Information Retrieval - ICTIR '16  
Findings suggest that this is a viable approach to estimating retrievability bias and that the number of queries required can be reduced to less than a quarter of what was previously thought necessary.  ...  This work explores the idea of using topical subsets of the collection for query generation and bias estimation to form a local estimate of bias which correlates with the global estimate of retrievability  ...  METHOD The focus of this work is to analyse whether or not retrievability bias can be accurately estimated by using a novel topic centric approach.  ... 
doi:10.1145/2970398.2970437 dblp:conf/ictir/WilkieA16 fatcat:pgk5d4gqhzfvjer7umsrsj3rmq

Sentiment diversification with different biases

Elif Aktolga, James Allan
2013 Proceedings of the 36th international ACM SIGIR conference on Research and development in information retrieval - SIGIR '13  
For this, we first infer the prior sentiment bias inherent in a controversial topic -the 'Topic Sentiment'.  ...  Then, we utilize this information in 3 different ways to diversify results according to various sentiment biases: (1) Equal diversification to achieve a balanced and unbiased representation of all sentiments  ...  To what extent does it make sense to consider biases for topical diversity? For instance, with an Outlier bias-like approach underrepresented query aspects could be highlighted in search results.  ... 
doi:10.1145/2484028.2484060 dblp:conf/sigir/AktolgaA13 fatcat:3ewdu3x5dvabparhbyqek22n5u

Bias and the limits of pooling

Chris Buckley, Darrin Dimmick, Ian Soboroff, Ellen Voorhees
2006 Proceedings of the 29th annual international ACM SIGIR conference on Research and development in information retrieval - SIGIR '06  
Drawbacks: How these methods interact with bias is unknown. The efficiency savings is likely insufficient to solve the problem. Encouraging different retrieval approaches.  ...  New approaches to building very large, reusable test collections are needed. Several possible approaches, with advantages and drawbacks, are briefly discussed here. Engineering the topics.  ... 
doi:10.1145/1148170.1148284 dblp:conf/sigir/BuckleyDSV06 fatcat:tr4kznfaxzfitf7btagfocjpzi

A comparison of pooled and sampled relevance judgments

Ian Soboroff
2007 Proceedings of the 30th annual international ACM SIGIR conference on Research and development in information retrieval - SIGIR '07  
This paper describes the approach taken in the TREC 2006 Terabyte Track: an initial shallow pool was judged to gather relevance information, which was then used to draw a random sample of further documents  ...  to judge.  ...  The resulting relevance judgments would then be biased towards participating retrieval systems and might unfairly rank new or alternative approaches [11] .  ... 
doi:10.1145/1277741.1277908 dblp:conf/sigir/Soboroff07 fatcat:nxpsjcdiwjhb5la4b6twdfp5tq

Bias–variance analysis in estimating true query model for information retrieval

Peng Zhang, Dawei Song, Jun Wang, Yuexian Hou
2014 Information Processing & Management  
The estimation of query model is an important task in language modeling (LM) approaches to information retrieval (IR).  ...  In this paper, we propose to study this tradeoff from a new perspective, i.e., the bias-variance tradeoff, which is a fundamental theory in statistics.  ...  Acknowledgement The authors would like to thank anonymous reviewers for their constructive comments.  ... 
doi:10.1016/j.ipm.2013.08.004 fatcat:4py4jibudrdlxamckcsd53n6te

Find me opinion sources in blogosphere

Xueke Xu, Songbo Tan, Yue Liu, Xueqi Cheng, Zheng Lin, Jiafeng Guo
2012 Proceedings of the fifth ACM international conference on Web search and data mining - WSDM '12  
To estimate TFM, we propose a topic-biased random walk to exploit both content and structural information to capture topic-biased salient information in the feed.  ...  Furthermore, we propose a language modeling approach to estimating opinion scores that is seamlessly integrated into the framework, where two language models, Topic-specific Opinion Model (TOM) and Topic-biased  ...  Following these requirements, we propose to use a mixture model with prior guidance to estimate TOM and a topic-biased random walk to estimate TFM.  ... 
doi:10.1145/2124295.2124366 dblp:conf/wsdm/XuTLCLG12 fatcat:csr75wmuojdeznnnu7wpman6ey

The Importance of Length Normalization for XML Retrieval

Jaap Kamps, Maarten de Rijke, B�rkur Sigurbj�rnsson
2005 Information retrieval (Boston)  
XML retrieval is a departure from standard document retrieval in which each individual XML element, ranging from italicized words or phrases to full blown articles, is a retrievable unit.  ...  We observe a length-bias introduced by the amount of smoothing, and show the importance of extreme length bias for XML retrieval.  ...  Acknowledgments We are grateful to our anonymous referees for their valuable comments.  ... 
doi:10.1007/s10791-005-0750-7 fatcat:dhtyf4jijrfwzno4rgfkdkzb5u

Length normalization in XML retrieval

Jaap Kamps, Maarten de Rijke, Börkur Sigurbjörnsson
2004 Proceedings of the 27th annual international conference on Research and development in information retrieval - SIGIR '04  
XML retrieval is a departure from standard document retrieval in which each individual XML element, ranging from italicized words or phrases to full blown articles, is a retrievable unit.  ...  We observe a length-bias introduced by the amount of smoothing, and show the importance of extreme length bias for XML retrieval.  ...  Acknowledgments We are grateful to our anonymous referees for their valuable comments.  ... 
doi:10.1145/1008992.1009009 dblp:conf/sigir/KampsRS04 fatcat:uyou4akxurhmvhf26x2co2epta

A Topic-Based Measure of Resource Description Quality for Distributed Information Retrieval [chapter]

Mark Baillie, Mark J. Carman, Fabio Crestani
2009 Lecture Notes in Computer Science  
To address this issue we propose to measure the relative entropy between topics obtained in a sample with respect to the complete collection.  ...  by samples which do not reflect the topical density of a collection.  ...  evaluation of information retrievability and bias [15] .  ... 
doi:10.1007/978-3-642-00958-7_43 fatcat:xz2fxclo4bgsdc2dt7ia2xz7zy

Theory of Retrieval

Leif Azzopardi
2015 Proceedings of the 2015 International Conference on Theory of Information Retrieval - ICTIR '15  
In this tutorial, we shall explain the concept of retrievability along with a number of retrievability measures, how it can be estimated and how it can be used for analysis.  ...  This is important because a document needs to be retrieved, before it can be judged for relevance.  ...  Psuedo Relevance Bias: how Pseudo Relevance is biased, and addressing that bias leads to performance improvements [16] . 5.  ... 
doi:10.1145/2808194.2809444 dblp:conf/ictir/Azzopardi15 fatcat:catxinspjvfwtjoznhabvqftwy

Bias and Fairness in Effectiveness Evaluation by Means of Network Analysis and Mixture Models

Kevin Roitero, Stefano Mizzaro, Michael Soprano
2019 Italian Information Retrieval Workshop  
We propose a systematic approach to identify bias and its causes, and to remove it, thus enforcing fairness in effectiveness evaluation by means of test collections.  ...  Information retrieval effectiveness evaluation is often carried out by means of test collections. Many works investigated possible sources of bias in such an approach.  ...  [8] , demonstrate that the evaluation is biased, and in particular that easy topics are better in recognising effective systems; in other words, a retrieval system to be effective needs to be effective  ... 
dblp:conf/iir/RoiteroMS19 fatcat:2qhxzlgwyfd2fd66syqelrm4qu

Power and bias of subset pooling strategies

Gordon V. Cormack, Thomas R. Lynam
2007 Proceedings of the 30th annual international ACM SIGIR conference on Research and development in information retrieval - SIGIR '07  
We define a method to estimate the random and systematic errors resulting from incomplete relevance assessments.  ...  Move-to-front pooling, previously reported to yield substantially better rank correlation, yields similar power, and lower bias, compared to fixed-depth pooling.  ...  We present a method to estimate the power and bias of pooling methods, and use our method to evaluate the effectiveness of several pooling alternatives as a function of adjudication effort.  ... 
doi:10.1145/1277741.1277934 dblp:conf/sigir/CormackL07a fatcat:dauyjhyt7vcshacwwikuwiordq

Bias and the limits of pooling for large collections

Chris Buckley, Darrin Dimmick, Ian Soboroff, Ellen Voorhees
2007 Information retrieval (Boston)  
Modern retrieval test collections are built through a process called pooling in which only a sample of the entire document set is judged for each topic.  ...  also exhibit the bias.  ...  It's important to get a wide variety of approaches to avoid unknown biases, and to detect when there is a problem.  ... 
doi:10.1007/s10791-007-9032-x fatcat:ocsix63ddzan7bgxoik3xj5dti

The retrievability of documents

Leif Azzopardi
2014 Proceedings of the 37th international ACM SIGIR conference on Research & development in information retrieval - SIGIR '14  
In this tutorial, we shall explain the concept of retrievability along with a number of retrievability measures, how it can be estimated and how it can be used for analysis.  ...  This is important because a document needs to be retrieved, before it can be judged for relevance.  ...  document (i.e. a pagecentric approach) and how the retrievability of all the documents can be estimated (i.e. a collection-centric approach).  ... 
doi:10.1145/2600428.2602298 dblp:conf/sigir/Azzopardi14a fatcat:5bvxa24rere7pe4jbwbgtpimxi

CWI at ImageCLEF 2008

Theodora Tsikrika, Henning Rode, Arjen P. de Vries
2008 Conference and Labs of the Evaluation Forum  
We also investigated a length prior and found that biasing towards images with longer descriptions than the ones retrieved by our language modelling approach is not beneficial.  ...  CWI used PF/Tijah, a flexible XML retrieval system, to evaluate image retrieval based on textual evidence in the context of the wikipediaMM task at ImageCLEF 2008.  ...  Our analysis indicated that the textual descriptions of the relevant images tend to be of equal length to the ones our approach retrieves, thus biasing towards images with richer descriptions is not beneficial  ... 
dblp:conf/clef/TsikrikaRV08 fatcat:7vnjf4kbdjg2jb7wqvnkgii5hi
« Previous Showing results 1 — 15 out of 84,195 results