Filters








43,428 Hits in 6.8 sec

Query-independent evidence in home page finding

Trystan Upstill, Nick Craswell, David Hawking
2003 ACM Transactions on Information Systems  
Another form of query-independent evidence, URL-type, has been shown to be beneficial on a home page finding task.  ...  In combination with URL-type the anchor text baseline was more useful for finding popular home pages, but URL-type with content was more useful for finding randomly selected home pages.  ...  QUERY-INDEPENDENT EVIDENCE The focus of the present study is on evaluating the potential contribution to home page finding of query-independent evidence: URL-type, in-degree, and PageRank.  ... 
doi:10.1145/858476.858479 fatcat:5yldmxgllba7niffou7ypxujbu

University of Glasgow at the Web Track: Dynamic Application of Hyperlink Analysis using the Query Scope

Vassilis Plachouras, Iadh Ounis, Cornelis Joost van Rijsbergen, Fidel Cacheda
2003 Text Retrieval Conference  
For the known item task, we employ the query scope in order to distinguish the named page queries from the home page queries, obtaining results close to the content and anchor text baseline.  ...  This year, our participation to the Web track aims at combining dynamically evidence from both content and hyperlink analysis.  ...  Run Known Item Finding Task For the known item finding task, we employ the query scope in order to discriminate between home page and named page queries.  ... 
dblp:conf/trec/PlachourasORC03 fatcat:etwqvd4iu5hpne2svzcj6m3vfq

Topic Distillation with Query-Dependent Link Connections and Page Characteristics

Mingfang Wu, Falk Scholer, Andrew Turpin
2011 ACM Transactions on the Web  
Moreover, we demonstrate that, at a different scope level, both local query-dependent outdegree and query-dependent indegree out-performed their global query-independent counterparts; and at the same scope  ...  Adding query-dependent indegree or page characteristics to query-dependent outdegree could have a small, but not significant, improvement.  ...  searching on the full-text of documents for particular search tasks such as site finding [Craswell et al. 2001a ] and home page finding [Upstill et al. 2003] .  ... 
doi:10.1145/1961659.1961660 fatcat:ztj3dlpxkvcjrhpr66vpvmbttq

The meaning of structure

Marijn Koolen
2011 SIGIR Forum  
For Web-centric search tasks, such as home page and named page finding, incoming link evidence is more effective than outgoing  ...  Home pages and other important Web pages tend to be pages with many incoming links, and link evidence such as indegree counts and PageRank proved highly effective.  ...  We also experiment with filtering links based on the semantic relatedness of the link documents and find that links between semantically related pages are more effective for identifying topically relevant  ... 
doi:10.1145/1988852.1988872 fatcat:ogps7l566fdijmfakefnizp27a

VT at TREC-2003: The Web Track Report

Rui Yang, Li Wang, Weiguo Fan, Wensi Xi, Ming Luo, Ye Zhou, Edward A. Fox
2003 Text Retrieval Conference  
We did well for named page finding task, but poorly on home page finding task. This indicates that home paging requires some additional evidence such as URL, Link information for effective ranking.  ...  Results In the end, we submit ten independent runs for this year's Web Track -five for the topic distillation task, five for the Name/Home page finding task.  ... 
dblp:conf/trec/YangWFXLZF03 fatcat:eh6yrgoidjap7fx2dds322pzuu

Relevant query feedback in statistical language modeling

Ramesh Nallapati, Bruce Croft, James Allan
2003 Proceedings of the twelfth international conference on Information and knowledge management - CIKM '03  
To validate our models, we considered anchor text of incoming links to a given document as feedback queries and performed experiments on the home-page retrieval task of TREC 2001.  ...  In this work, we investigate relevant query feedback, in which we update a document's representation based on a set of relevant queries.  ...  Any opinions, findings and conclusions or recommendations expressed in this material are the author(s) and do not necessarily reflect those of the sponsor.  ... 
doi:10.1145/956863.956973 dblp:conf/cikm/NallapatiCA03 fatcat:it62izsgzrgdlc3hoblhuh2lnm

Ranking Web Pages Using Collective Knowledge

Falah Hassan Al-akashi, Diana Inkpen
2011 Text Retrieval Conference  
We ranked term queries in different ways, depending if they were found in Wikipedia pages or not.  ...  Our approach aims to efficiently index web documents by employing a hybrid technique in which web documents are indexed in such a way that knowledge available in the Wikipedia and in meta-content is efficiently  ...  It is known that full-text relevance ranking is not particularly effective for home page finding [4] . Other potentially useful evidence is query-independent.  ... 
dblp:conf/trec/Al-akashiI11 fatcat:2wsv7afchjevxo4p2ajcpagvoe

Relevant query feedback in statistical language modeling

Ramesh Nallapati, Bruce Croft, James Allan
2003 Proceedings of the twelfth international conference on Information and knowledge management - CIKM '03  
To validate our models, we considered anchor text of incoming links to a given document as feedback queries and performed experiments on the home-page retrieval task of TREC 2001.  ...  In this work, we investigate relevant query feedback, in which we update a document's representation based on a set of relevant queries.  ...  Any opinions, findings and conclusions or recommendations expressed in this material are the author(s) and do not necessarily reflect those of the sponsor.  ... 
doi:10.1145/956958.956973 fatcat:s7kjvoqa7bbypjun42isfgqzya

Linking wikipedia to the web

Rianne Kaptein, Pavel Serdyukov, Jaap Kamps
2010 Proceeding of the 33rd international ACM SIGIR conference on Research and development in information retrieval - SIGIR '10  
We have constructed a test collection of 53 topics, which are Wikipedia pages on different entities. Our findings are that the anchor text index is a very effective method to retrieve home pages.  ...  We investigate the task of finding links from Wikipedia pages to external web pages.  ...  Besides the internal evidence, we also looked for external evidence to find home pages.  ... 
doi:10.1145/1835449.1835642 dblp:conf/sigir/KapteinSK10 fatcat:bu5u7ukmarefvj7iwujej7uxcq

Is Wikipedia link structure different?

Jaap Kamps, Marijn Koolen
2009 Proceedings of the Second ACM International Conference on Web Search and Data Mining - WSDM '09  
In this paper, we investigate the difference between Wikipedia and Web link structure with respect to their value as indicators of the relevance of a page for a given topic of request.  ...  Third, when incorporating link evidence in the retrieval model, for Wikipedia the global link evidence fails and we have to take the local context into account.  ...  [7] studies query independent evidence for a mixed query set of topic distillation, home page finding and named-page finding topics, and find that, in order of impact, PageRank, indegree, URL length  ... 
doi:10.1145/1498759.1498831 dblp:conf/wsdm/KampsK09 fatcat:x5fmfxcxznguvcwivsdsuvendq

Intelligent web page retrieval using Wikipedia knowledge

Falah H. Al-akashi, Diana Inkpen
2012 Proceedings of the 2nd International Conference on Web Intelligence, Mining and Semantics - WIMS '12  
Our index contains separate information about the frequency of the terms in Wikpedia articles, in home pages, and in other types of web pages, instead of using a generic term frequency for the whole text  ...  for different aspects of the queries).  ...  It is known that full-text relevance ranking is not particularly effective for home page finding [4] . Other potentially useful evidence is query-independent.  ... 
doi:10.1145/2254129.2254192 dblp:conf/wims/Al-akashiI12 fatcat:i7o474s275fmjc43qpvdljji5e

Overview of the TREC-2002 Web Track

Nick Craswell, David Hawking
2002 Text Retrieval Conference  
The topic distillation task involved finding pages which were relevant, but also had characteristics which would make them desirable inclusions in a distilled list of key pages.  ...  The named page task is a variant of last year's homepage finding task.  ...  grateful to Ed Fox of Virginia Tech for providing the machine and network connection to support the crawl and to Ian Soboroff of NIST for facilitating the crawl and also for his invaluable assistance in  ... 
dblp:conf/trec/CraswellH02 fatcat:flpihsutujf7hki22zgavugu2m

University of Glasgow at WebCLEF 2005: Experiments in Per-Field Normalisation and Language Specific Stemming [chapter]

Craig Macdonald, Vassilis Plachouras, Ben He, Christina Lioma, Iadh Ounis
2006 Lecture Notes in Computer Science  
Both the documents and the queries are written in a wide range of European languages. A challenge in this setting is to detect the language of documents and topics, and to process them appropriately.  ...  We participated in the WebCLEF 2005 monolingual task.  ...  Regarding the two types of queries, all our submitted runs performed consistently better on the named page finding queries, than on the home page finding queries.  ... 
doi:10.1007/11878773_100 fatcat:tewj5cvwjnh7phywb6ggyor5aq

Interactive Internet search

Peter Bruza, Robert McArthur, Simon Dennis
2000 Proceedings of the 23rd annual international ACM SIGIR conference on Research and development in information retrieval - SIGIR '00  
Cognitive load was • measured using a secondary digit-monitoring task to quantify the effort of the user in various search states; independent relevance judgements were employed to gauge the quality of  ...  Time was monitored in various search states.  ...  Acknowledgements The work reported in this paper has been funded in part by the Australian Research Council, Key Center for Human Factors and Applied Cognitive Psychology at the University of Queensland  ... 
doi:10.1145/345508.345598 dblp:conf/sigir/BruzaMD00 fatcat:ehgs7jsjznduzmagi57ttjokdy

Usefulness of quality click-through data for training

Craig Macdonald, Iadh Ounis
2009 Proceedings of the 2009 workshop on Web Search Click Data - WSCD '09  
In this work, we examine the usefulness of high-quality clickthrough data for training an IR system, on searching the .gov vertical domain of the Web.  ...  To obtain these parameter settings, quality training is usually required, where assessors have manually labelled the relevance of retrieved items for many queries.  ...  In Proceedings of SIGIR 2006, pages 3-10.  ... 
doi:10.1145/1507509.1507521 dblp:conf/wsdm/MacdonaldO09 fatcat:toz2aosyebbsfcomnl7xcwm4cm
« Previous Showing results 1 — 15 out of 43,428 results