Showing papers by "Jeffrey Dean published in 2005"

Multi-stage query processing system and method for use with tokenspace repository

Abstract: A multi-stage query processing system and method enables multi-stage query scoring, including “snippet” generation, through incremental document reconstruction facilitated by a multi-tiered mapping scheme. At one or more stages of a multi-stage query processing system a set of relevancy scores are used to select a subset of documents for presentation as an ordered list to a user. The set of relevancy scores can be derived in part from one or more sets of relevancy scores determined in prior stages of the multi-stage query processing system. In some embodiments, the multi-stage query processing system is capable of executing one or more passes on a user query, and using information from each pass to expand the user query for use in a subsequent pass to improve the relevancy of documents in the ordered list.

Data compression of large scale data stored in sparse tables

Abstract: A method of compressing data in a table data structure begins by accessing a data set within the table data structure, the data set having associated therewith a range of rows of the table data structure. Data items in the data set are represented by key-value pairs. The method includes applying a first compression to the values of the key-value pairs in the data set to produce a first compressed output; applying a second compression, distinct from the first compression, to the keys of the key-value pairs in the data set to produce a second compressed output; and applying a third compression to the first compressed output and second compressed output to produce a first compressed output block, wherein the third compression is distinct from the first compression and second compression.

Storing a sparse table using locality groups

Abstract: Each of a plurality of data items is stored in a table data structure. The table structure includes a plurality of columns. Each of the columns is associated with one of a plurality of locality groups. Each locality group is stored as one or more corresponding locality group files that include the data items in the columns associated with the respective locality group. In some embodiments, the columns of the table data structure may be grouped into groups of columns and each group of columns is associated with one of a plurality of locality groups. Each locality group is stored as one or more corresponding locality group files that include the data items in the group of columns associated with the respective locality group.

Systeme de traitement de demandes a etages multiples et procede d'utilisation sur un referentiel comportant des indices associes

Abstract: Systeme de traitement de demandes a etages multiples et procede permettant d'evaluer des demandes a etages multiples, y compris la generation 'd'entrefilets', par l'intermediaire de la reconstruction incrementielle de documents facilitee par une structure de mise en correspondance a niveaux multiples. A un ou plusieurs des etages d'un systeme de traitement de demandes a etages multiples, on utilise un ensemble d'evaluation d'adequation afin de selectionner un sous-ensemble de documents afin de les presenter a un utilisateur sous forme de liste ordonnee. Cet ensemble d'evaluations d'adequation peut provenir en partie d'un ou de plusieurs ensembles d'evaluations d'adequation determines dans des etages prealables de ce systeme. Dans quelques modes de realisation, ce systeme est capable d'executer un ou plusieurs passages sur une demande emanant d'un utilisateur et d'utiliser les informations acquises a chaque passage afin d'etendre la demande utilisateur, dans le but de la mettre en application dans un passage ulterieur et ainsi d'ameliorer l'adequation des documents de la liste ordonnee.