50,443 Hits in 3.7 sec

Approximate distributed metric-space search

Veronica Gil-Costa, Mauricio Marin
2011 Proceedings of the 9th workshop on Large-scale and distributed informational retrieval - LSDS-IR '11  
This paper proposes an approximate search algorithm for metric space search which is suitable for distributed search engines.  ...  At steady state search engine operation, the proposed algorithm calculates exact answers to queries whereas at peak traffic it calculates approximate answers.  ...  To prevent from saturation, the search engine temporarily responds with approximate answers for selected queries.  ... 
doi:10.1145/2064730.2064736 fatcat:refynahmkjbylpeqfsukmeknay

A metric cache for similarity search

Fabrizio Falchi, Claudio Lucchese, Salvatore Orlando, Raffaele Perego, Fausto Rabitti
2008 Proceeding of the 2008 ACM workshop on Large-Scale distributed systems for information retrieval - LSDS-IR '08  
been proved effective for traditional Web search engines.  ...  It is able to answer with exact and approximate results: even when an exact match is not present in cache, our cache may return an approximate result set with quality guarantees.  ...  RELATED WORK The research topics more related to our work are query result caching in Web search engines, and techniques for approximate searching in metric spaces. Query result caching.  ... 
doi:10.1145/1458469.1458473 dblp:conf/cikm/FalchiLOPR08 fatcat:4thbgn2zyrdo3apo4jutpck3l4

Developing a Meta-suggestion Engine for Search Queries [article]

Seungmin Kim, EunChan Na, Seong Baeg Kim
2022 arXiv   pre-print
Typically, search engines provide query suggestions to assist users in the search process. Query suggestions are very important for improving users search experience.  ...  Some search engines do not provide query suggestions, making searches difficult for users. These query suggestion vulnerabilities degrade the user's search experience.  ...  We evaluated the baseline and MSE with the previously described evaluation metrics. engine is better at predicting the user's next query.  ... 
arXiv:2110.12594v2 fatcat:7zciyhvn4jglxouhgstqq7un4e

Counterfactual Estimation and Optimization of Click Metrics in Search Engines

Lihong Li, Shunbao Chen, Jim Kleban, Ankur Gupta
2015 Proceedings of the 24th International Conference on World Wide Web - WWW '15 Companion  
The key challenge is the counterfactual nature: in the case of Web search, any change to a component of the search engine may result in a different search result page for the same query, but we normally  ...  Consequently, it appears impossible to accurately estimate online metrics that depend on user feedback, unless the new engine is actually run to serve live users and compared with a baseline in a controlled  ...  Acknowledgements We thank Leon Bottou, Chris Burges, Nick Craswell, Susan Dumais, Jianfeng Gao, John Platt, Ryen White, and Yinzhe Yu for helpful discussions.  ... 
doi:10.1145/2740908.2742562 dblp:conf/www/LiCKG15 fatcat:xo5i465tv5cttk2j7tqww4tmta

Toward Predicting the Outcome of an A/B Experiment for Search Relevance

Lihong Li, Jin Young Kim, Imed Zitouni
2015 Proceedings of the Eighth ACM International Conference on Web Search and Data Mining - WSDM '15  
In this work, inspired by recent successes of offline evaluation techniques for recommender systems, we study an alternative that uses historical search log to reliably predict online click-based metrics  ...  Extensive experimental results based on large-scale real search data from a major commercial search engine in the US market demonstrate our approach is promising and has potential for wide use in Web search  ...  Acknowledgement We thank Dongwoo Kim for help in our experiments, and the anonymous reviewers for numerous suggestions that improved the presentation of the paper.  ... 
doi:10.1145/2684822.2685311 dblp:conf/wsdm/LiKZ15 fatcat:gf4ibaghg5fihpmyn6bxs5pzke

Counterfactual Estimation and Optimization of Click Metrics for Search Engines [article]

Lihong Li and Shunbao Chen and Jim Kleban and Ankur Gupta
2014 arXiv   pre-print
The key challenge is the counterfactual nature: in the case of Web search, any change to a component of the search engine may result in a different search result page for the same query, but we normally  ...  Consequently, it appears impossible to accurately estimate online metrics that depend on user feedback, unless the new engine is run to serve users and compared with a baseline in an A/B test.  ...  In this paper, we advocate the use of causal inference techniques from statistics to perform unbiased offline evaluation of click metrics for search engines.  ... 
arXiv:1403.1891v2 fatcat:fb6k5zsulbb23jl3tnd5is4pn4

Auditing Search Engines for Differential Satisfaction Across Demographics

Rishabh Mehrotra, Ashton Anderson, Fernando Diaz, Amit Sharma, Hanna Wallach, Emine Yilmaz
2017 Proceedings of the 26th International Conference on World Wide Web Companion - WWW '17 Companion  
We first explain the pitfalls of na\"ively comparing the behavioral metrics that are commonly used to evaluate search engines.  ...  We then propose three methods for measuring latent differences in user satisfaction from observed differences in evaluation metrics.  ...  DISCUSSION Internally auditing search engines for equal access is much more complicated than comparing evaluation metrics for demographically binned search impressions.  ... 
doi:10.1145/3041021.3054197 dblp:conf/www/MehrotraADSWY17 fatcat:zzjtzgp6cvhuddgfuhkhlycume

Caching content-based queries for robust and efficient image retrieval

Fabrizio Falchi, Claudio Lucchese, Salvatore Orlando, Raffaele Perego, Fausto Rabitti
2009 Proceedings of the 12th International Conference on Extending Database Technology Advances in Database Technology - EDBT '09  
has been proven effective for traditional Web search engines.  ...  In this paper we investigate the possibility of caching the answers to content-based image retrieval queries in metric space, with the aim of reducing the average cost of query processing, and boosting  ...  Our cache instead exploits the metric property of the distance measure for evaluating the quality of the approximate results that can be returned.  ... 
doi:10.1145/1516360.1516450 dblp:conf/edbt/FalchiLOPR09 fatcat:zzgddt63qvcuzostajo436rb44

Diversifying search results

Rakesh Agrawal, Sreenivas Gollapudi, Alan Halverson, Samuel Ieong
2009 Proceedings of the Second ACM International Conference on Web Search and Data Mining - WSDM '09  
We propose an algorithm that well approximates this objective in general, and is provably optimal for a natural special case.  ...  We demonstrate empirically that our algorithm scores higher in these generalized metrics compared to results produced by commercial search engines.  ...  The results used in the evaluation of the commercial search engines are based on the actual documents returned for the queries issued.  ... 
doi:10.1145/1498759.1498766 dblp:conf/wsdm/AgrawalGHI09 fatcat:j62yaufvcjgulpe6dspupn7m7y

Predicting user preferences

Pavel Sirotkin
2020 Zenodo  
The many metrics employed for the evaluation of search engine results have not themselves been conclusively evaluated.  ...  We also show that considering more results for a given query can impair rather than improve a metric's ability to predict user preferences.  ...  For every query, the top 50 results were fetched from a major web search engine.  ... 
doi:10.5281/zenodo.4133313 fatcat:g3bzpsdm3rhnbgqbrxi3sm227m

IDEBench: A Benchmark for Interactive Data Exploration [article]

Philipp Eichmann, Carsten Binnig, Tim Kraska, Emanuel Zgraggen
2018 arXiv   pre-print
As a second contribution, this paper evaluates and discusses the performance results of selected IDE query engines using our benchmark.  ...  on metrics that capture the trade-off between query performance and quality of the result.  ...  analytical database systems, approximate query processing engines, as well as specialized engines for IDE) that are used today in order to execute IDE workloads.  ... 
arXiv:1804.02593v1 fatcat:4bzoyltuazbu7ndtcuwtg2xx6e

A framework for determining necessary query set sizes to evaluate web search effectiveness

Eric C. Jensen, Steven M. Beitzel, Ophir Frieder, Abdur Chowdhury
2005 Special interest tracks and posters of the 14th international conference on World Wide Web - WWW '05  
engines across 896 queries and the single best result for each of those queries.  ...  We also find that the number of queries needed for a repeatable evaluation in a dynamic environment such as the web is much higher than previously studied.  ...  Although it focuses on deep pooling for recall-oriented evaluation, recent meta-evaluation has shown that precision-oriented metrics require more queries to provide a stable evaluation [2] .  ... 
doi:10.1145/1062745.1062926 dblp:conf/www/JensenBFC05 fatcat:dyky6j354bbrhm5ih24scwpd74

On measuring performances of C-SPARQL and CQELS [article]

Xiangnan Ren and Houda Khrouf and Zakia Kazi-Aoul and Yousra Chabchoub and Olivier Curé
2016 arXiv   pre-print
Nevertheless, these benchmarks lack an in-depth performance evaluation as some measurement metrics have not been considered.  ...  The main goal of this paper is to analyze the performance of two popular RSP engines, namely C-SPARQL and CQELS, when varying a set of performance metrics.  ...  -X: (3) window size We use window size as a performance metric for RSP engines.  ... 
arXiv:1611.08269v1 fatcat:p5mgtspoyvbkrjfsr5b53u3cya


Firas Abuzaid, Xi Wu, Jeff Naughton, Peter Bailis, Matei Zaharia, Peter Kraft, Sahaana Suri, Edward Gan, Eric Xu, Atul Shenoy, Asvin Ananthanarayan, John Sheu (+1 others)
2018 Proceedings of the VLDB Endowment  
We evaluate these optimizations on several realworld production applications, and find that DIFF in MB SQL can outperform state-of-the-art engines by up to an order of magnitude.  ...  In response, we propose the DIFF operator, a relational aggregation operator that unifies the core functionality of these engines with declarative relational query processing.  ...  Acknowledgments We thank Kexin Rong, Hector Garcia-Molina, our colleagues in the Stanford DAWN Project, and the anonymous VLDB reviewers for their detailed feedback on earlier drafts of this work.  ... 
doi:10.14778/3297753.3297761 fatcat:bq224dlk35fm5aoisbyvdtbqjq

Search shortcuts

Ranieri Baraglia, Fidel Cacheda, Victor Carneiro, Diego Fernandez, Vreixo Formoso, Raffaele Perego, Fabrizio Silvestri
2009 Proceedings of the third ACM conference on Recommender systems - RecSys '09  
Different techniques for analyzing and extracting information from query logs, as well as new metrics and techniques for measuring the effectiveness of recommendations are proposed and evaluated.  ...  The recommendation of queries, known as query suggestion, is a common practice on major Web Search Engines.  ...  Theoretical model and evaluation metric Let U = {u|u is a user} be the set of all users of a search engine.  ... 
doi:10.1145/1639714.1639729 dblp:conf/recsys/BaragliaCCFFPS09 fatcat:733wnpdk2vbcfl3zajo2u7dary
« Previous Showing results 1 — 15 out of 50,443 results