Topic
Ranking (information retrieval)
About: Ranking (information retrieval) is a research topic. Over the lifetime, 21109 publications have been published within this topic receiving 435130 citations.
Papers published on a yearly basis
Papers
More filters
01 Apr 1998
TL;DR: Inquireirus as discussed by the authors is a meta search engine that works by downloading and analyzing the individual documents, instead of working with the list of documents and summaries returned by search engines, as current meta search engines typically do.
Abstract: World Wide Web (WWW) search engines (e.g. AltaVista, Infoseek, HotBot, etc.) have a number of deficiencies including: periods of downtime, low coverage of the WWW, inconsistent and inefficient user interfaces, out of date databases, poor relevancy ranking and precision, and difficulties with spamming techniques. Meta search engines have been introduced which address some of these and other difficulties in searching the WWW. However, current meta search engines retain some of these difficulties and may also introduce their own problems (e.g. reduced relevance because one or more of the search engines returns results with poor relevance). We present Inquirus, the NECI meta search engine, which addresses many of the deficiencies in current techniques. Rather than working with the list of documents and summaries returned by search engines, as current meta search engines typically do, the Inquirus meta search engine works by downloading and analyzing the individual documents. The Inquirus meta search engine makes improvements over existing search engines in a number of areas, e.g.: more useful document summaries incorporating query term context, identification of both pages which no longer exist and pages which no longer contain the query terms, advanced detection of duplicate pages, improved document ranking using proximity information, dramatically improved precision for certain queries by using specific expressive forms, and quick jump links and highlighting when viewing the full documents.
149 citations
TL;DR: A new theoretical framework for interactive retrieval is proposed, and the relationship of this rule to the classical PRP is described, and issues of further research are pointed out.
Abstract: The classical Probability Ranking Principle (PRP) forms the theoretical basis for probabilistic Information Retrieval (IR) models, which are dominating IR theory since about 20 years. However, the assumptions underlying the PRP often do not hold, and its view is too narrow for interactive information retrieval (IIR). In this article, a new theoretical framework for interactive retrieval is proposed: The basic idea is that during IIR, a user moves between situations. In each situation, the system presents to the user a list of choices, about which s/he has to decide, and the first positive decision moves the user to a new situation. Each choice is associated with a number of cost and probability parameters. Based on these parameters, an optimum ordering of the choices can the derived--the PRP for IIR. The relationship of this rule to the classical PRP is described, and issues of further research are pointed out.
149 citations
Patent•
09 Mar 2006
TL;DR: A computer system and method for processing search query result includes identifying a plurality of result pages in response to a search query submitted from a computing device directed to a collection of pages, determining a relevancy ranking of the result pages according with a multiple dimension parameter set that includes metrics relating to the search query itself and also includes metrics unique to a subscriber associated with the search queries.
Abstract: A computer system and method a computer system and method for processing a search query result includes identifying a plurality of result pages in response to a search query submitted from a computing device directed to a collection of pages, determining a relevancy ranking of the result pages in accordance with a multiple dimension parameter set that includes metrics relating to the search query itself and also includes metrics unique to a subscriber associated with the search query, and providing the result pages in accordance with the determined relevancy ranking. This provides an active ranking process for the search results before they are provided to a user.
149 citations
Patent•
31 Jul 2000
TL;DR: An economic, scalable machine learning system and process performed document (concept) classification with high accuracy using large topic schemes, including large hierarchical topic schemes as discussed by the authors, which includes training and concept classification processes.
Abstract: An economic, scalable machine learning system and process perform document (concept) classification (210) with high accuracy using large topic schemes, including large hierarchical topic schemes. One or more highly relevant classification topics is suggested for a given document (concept) to be classified (210). The invention includes training (200) and concept classification (210) processes. The invention also provides methods that may be used as part of the training and/or concept classification processes, including: a method of scoring (303) the relevance of features in training concepts, a method of ranking concepts based on relevance score, and a method of voting on topics associated with an input concept. In a preferred embodiment, the invention is applied to the legal (case law) domain, classifying legal concepts (rules of law) according to a proprietary legal topic classification scheme (a hierarchical scheme of areas of law).
148 citations