9,949 Hits in 6.9 sec

Classifying queries submitted to a vertical search engine

Richard Berendsen, Bogomil Kovachev, Edgar Meij, Maarten de Rijke, Wouter Weerkamp
2011 Proceedings of the 3rd International Web Science Conference on - WebSci '11  
We propose and motivate a scheme for classifying queries submitted to a people search engine.  ...  We specify a number of features for automatically classifying people queries into the proposed classes and examine the effectiveness of these features.  ...  Classifying queries submitted to an engine as they come in is useful for a number of reasons.  ... 
doi:10.1145/2527031.2527055 dblp:conf/websci/BerendsenKMRW11 fatcat:6myysntbxvctrckl2fsqsnyax4

When video search goes wrong

Christoph Kofler, Linjun Yang, Martha Larson, Tao Mei, Alan Hanjalic, Shipeng Li
2012 Proceedings of the 20th ACM international conference on Multimedia - MM '12  
Our context-aware query failure prediction approach uses a combination of user indicators and engine indicators to predict whether a particular query is likely to fail in the context of a particular search  ...  Users face increased difficulty in formulating effective queries and search engines must deploy highly effective algorithms to provide relevant results.  ...  For the purposes of this paper, we focus on sessions containing at least one query submitted to the video vertical of the search engine.  ... 
doi:10.1145/2393347.2393395 dblp:conf/mm/KoflerYLMHL12 fatcat:2jm64oxe5jedtfxdj566t6wlne


Ming Yue, Zhicheng Dou, Sha Hu, Jinxiu Li, Xiao-Jie Wang, Ji-Rong Wen
2016 NTCIR Conference on Evaluation of Information Access Technologies  
In the Query Understanding subtask, we combine the extracted candidates from search engine suggestions and Wikipeida, and classify their verticals after clustering and ranking them.  ...  In the Vertical Incorporating subtask, we provide a general method for adapting traditional diversity algorithms to deal with predefined subtopics with classified verticals in diversification.  ...  However, with an ambiguous or broad query, a retrieval system or search engine may misunderstand users' interests, by simply comparing the query with the corpus and returning a ranked result list.  ... 
dblp:conf/ntcir/YueDHLWW16 fatcat:g65sipv35zcknbdirdli4lv6qa

Site-searching strategies of searchers referred from search engines

Adan Ortiz-Cordova, Bernard J. Jansen
2013 Proceedings of the American Society for Information Science and Technology  
who submit a query to the major search engine that is part of a URL and then submit specific queries to the site-search engine, and (3) the persisters who submit the exact type of query on both the search  ...  Of the six, the three major searching strategies are (1) the explorers who submit a broad query on the major search engine and then submit multiple broad queries on the site-search engine, (2) the navigators  ...  ACKNOWLEDGMENTS We would like to thank for allowing us to implement our data collection tool and have access to their database.  ... 
doi:10.1002/meet.14505001050 fatcat:jhdnst5zfjdsdhhlrvudc6dri4

Database technologies for electronic commerce [chapter]

Rakesh Agrawal, Ramakrishnan Srikant, Yirong Xu
2002 VLDB '02: Proceedings of the 28th International Conference on Very Large Databases  
Then the layer submits the transformed query to the underlying database engine, and returns the query results.  ...  The same query is also automatically submitted to Amazon and Google (the Google search is restricted to the Amazon site to keep the comparison fair). Figure 1 shows a snapshot of the demonstration.  ... 
doi:10.1016/b978-155860869-6/50107-4 dblp:conf/vldb/AgrawalSX02 fatcat:izdashcpgjcpldhle25fgnyh4i

Image Search Reranking [article]

V Rajakumar, Vipeen V Bopche
2014 arXiv   pre-print
While model learning needs manual labeling of the results for a some limited queries, the resulting model is query autonomous and therefore applicable to any other query .Examples are given for a selection  ...  A number of methods are differentiated for this re-ranking. The high ranked images are used as noisy data and a k means algorithm for classification is learned to rectify the ranking further.  ...  Google search engine for this we are connecting the Google search engine by the help of web browser and submitting the query.  ... 
arXiv:1402.2232v1 fatcat:xvwaetpnt5db7lbuz7ls3hhwxi

Searchable web sites recommendation

Yang Song, Nam Nguyen, Li-wei He, Scott Imig, Robert Rounthwaite
2011 Proceedings of the fourth ACM international conference on Web search and data mining - WSDM '11  
Keywords Vertical Search Engines • The search results are often presented with a more appropriate format or user interface; • Since each web site usually focuses on a specific domain, the user has to do  ...  Given a query, our system will recommend a list of searchable web sites ranked by relevance, which can be used to complement the web page results and ads from a search engine.  ...  the query to a general search engine.  ... 
doi:10.1145/1935826.1935890 dblp:conf/wsdm/SongNHIR11 fatcat:247yxjfhenhr5lxmp7mcfzjyea

Evaluating large-scale distributed vertical search

Ke Zhou, Ronan Cummins, Mounia Lalmas, Joemon Jose
2011 Proceedings of the 9th workshop on Large-scale and distributed informational retrieval - LSDS-IR '11  
As various distributed vertical search techniques (also as known as aggregated search) have been proposed, it is crucial that we need to be able to properly evaluate those systems on a large-scale standard  ...  A test collection for aggregated search requires a number of verticals, each populated by items (e.g. documents, images, etc) of that vertical type, a set of topics expressing information needs relating  ...  To boost the accuracy of the classification provide in step 1, we submitted the "titles" of all of the classified pages to existing vertical search engines.  ... 
doi:10.1145/2064730.2064735 fatcat:4ldgfwsu3ravji74l4a4l26fsu

Overview of the TREC 2014 Federated Web Search Track

Thomas Demeester, Dolf Trieschnigg, Dong Nguyen, Djoerd Hiemstra, Ke Zhou
2014 Text Retrieval Conference  
The TREC Federated Web Search track facilitates research on federated web search, by providing a large realistic data collection sampled from a multitude of online search engines.  ...  The FedWeb 2013 Resource Selection and Results Merging tasks are again included in FedWeb 2014, and we additionally introduced the task of vertical selection.  ...  ACKNOWLEDGMENTS This work was funded by the Folktales As Classifiable Texts (FACT) project in The Netherlands, by the Dutch national project COMMIT, and by Ghent University -iMinds in Belgium.  ... 
dblp:conf/trec/DemeesterTNHZ14 fatcat:nqjxjeimuvc5tagautkx2cl3ni

Simple May Be Best - A Simple and Effective Method for Federated Web Search via Search Engine Impact Factor Estimation

Shan Jin, Man Lan
2014 Text Retrieval Conference  
In this work, we propose a Search engine Impact Factor (SEIF) estimation approach to improve the performance of vertical and resource selection.  ...  In consideration of the connections between vertical and search engine (i.e., a vertical could contain multiple resources), we address the two tasks in an iterative way.  ...  For each given query, we use this SEIFscore to rank search engines. Outputs of VS System Generally a query may be relevant to multiple search engines with the same vertical label.  ... 
dblp:conf/trec/JinL14 fatcat:uaurglvmu5glxnvjcwiawgbkja

What Users Ask a Search Engine

Michael Völske, Pavel Braslavski, Matthias Hagen, Galina Lezina, Benno Stein
2015 Proceedings of the 24th ACM International on Conference on Information and Knowledge Management - CIKM '15  
We analyze the question queries submitted to a large commercial web search engine to get insights about what people ask, and to better tailor the search results to the users' needs.  ...  The resulting classifier is then transferred to the web search questions.  ...  Pavel Braslasvki's and Galina Lezina's current work is partially supported by RFBR, research project #14-07-00589-a.  ... 
doi:10.1145/2806416.2806457 dblp:conf/cikm/VolskeBHLS15 fatcat:ye3zu4ji2ndhldbeffhb3d2z2a

Evaluating verbose query processing techniques

Samuel Huston, W. Bruce Croft
2010 Proceeding of the 33rd international ACM SIGIR conference on Research and development in information retrieval - SIGIR '10  
In this paper, we examine query processing techniques which can be applied to verbose queries prior to submission to a search engine in order to improve the search engine's results.  ...  We evaluated the output of two search engines using queries from a CQA service and our results show that, among a broad range of techniques, the most effective approach is to simply reduce the length of  ...  In order to construct the "difficult" query set, candidate queries were submitted to a web search engine (Yahoo! Search).  ... 
doi:10.1145/1835449.1835499 dblp:conf/sigir/HustonC10 fatcat:zf7sxkjtjbegbpnqu7ph3txaha

A Comparative Study of Hidden Web Crawlers

Sonali Gupta, Komal Kumar Bhatia
2014 International Journal of Computer Trends and Technology  
A large amount of data on the WWW remains inaccessible to crawlers of Web search engines because it can only be exposed on demand as users fill out and submit forms.  ...  Research on Hidden Web has emerged almost a decade ago with the main line being exploring ways to access the content in online databases that are usually hidden behind search forms.  ...  Search systems using such vertical schema are called vertical search engines.  ... 
doi:10.14445/22312803/ijctt-v12p122 fatcat:urimdozni5cc5atetum2cjmoka

Deep Web Efficacy: A Knowledge Perspective

Manpreet Singh Sehgal, Jay Shankar Prasad
2018 International Journal of Applied Engineering Research  
This paper presents a comparative study of such crawlers mentioning their merits and demerits so as to help readers to find the research gaps and unhide the deep web for knowledge perspective.  ...  The research on the abilities of web crawlers and the efforts to design crawlers to extract this data hidden in the electronic databases (by automatic filling search interfaces and by other mechanisms)  ...  The job of a hidden web crawler is to process the query forms and submit them as well to retrieve (download) the result pages to be used later with the search engine's index structure as depicted in Figure  ... 
doi:10.37622/ijaer/13.22.2018.15544-15555 fatcat:4mio4l7t3bhehlwulz7o34soja

Learning to aggregate vertical results into web search results

Jaime Arguello, Fernando Diaz, Jamie Callan
2011 Proceedings of the 20th ACM international conference on Information and knowledge management - CIKM '11  
We present 3 general approaches that address these challenges in different ways and compare their results across a set of 13 verticals and 1070 queries.  ...  Aggregated search is the task of integrating results from potentially multiple specialized search services, or verticals, into the Web search results.  ...  As before, given a query, every block-pair i, j ∈ Bq, where one is a vertical-and the other a non-vertical block, is submitted to the appropriate classifier.  ... 
doi:10.1145/2063576.2063611 dblp:conf/cikm/ArguelloDC11 fatcat:x4bi7owrdbd65arqv4o643q6tu
« Previous Showing results 1 — 15 out of 9,949 results