Building Pseudo-Desktop Collections
نویسندگان
چکیده
Research on the desktop search has been constrained by the lack of reusable test collections. This led to a high entry barrier for new researchers and difficulty in the comparative evaluation of existing methods. To address this point, we introduce a method for creating reusable pseudo-desktop collections by gathering documents and generating queries that have similar characteristics to actual collections. Our method involves a new query generation method and a technique for evaluating the similarity of generated queries with user-generated queries.
منابع مشابه
Towards “Cranfield” Test Collections for Personal Data Search Evaluation
Desktop archives are distinct from sources for which shared “Cranfield” information retrieval test collectionshave been created to date. Differences associated with desktop collections include: they are personal to the archive owner, the owner has personal memories about the items contained within them, and only the collection owner can rate the relevance of items retrieved in response to their...
متن کاملConverting Desktop into a Personal Activity Dataset
The current experiments on personalization in information retrieval are limited to the available collections of the real world data. While a number of publications exploited user interaction with Desktop, often these experiments are neither repeatable nor comparable. In this paper we elaborate on the need for logging the Desktop activity data and creating a common collection for Desktop search ...
متن کاملECIR WORKSHOP REPORT Workshop on Evaluating Personal Search
The first ECIR workshop on Evaluating Personal Search was held on 18 April 2011 in Dublin, Ireland. The workshop consisted of 6 oral paper presentations and several discussion sessions. This report presents an overview of the scope and contents of the workshop and outlines the major outcomes. 1 0BIntroduction Personal Search (PS) refers to the process of searching within one’s personal space of...
متن کاملFreemix: Social Networking Meets Data
This paper introduces the Freemix platform, a framework for building social networking applications that connect people with data. Freemix provides people working with ”desktop” data (such as spreadsheets, XML collections and small databases) or structured web data (RSS, ATOM news feeds, etc.) a means to publish their data in a common translated format suitable for reuse. Once this data is avai...
متن کاملDynamic Collections in Indri
Text search engines have historically been designed for unchanging collections of documents. While this is fine for many applications, a growing number of important applications in news, finance, law and desktop search require indexes that can be efficiently updated. Previous research into supporting dynamic collections revolves around incremental methods. Incremental systems are optimized for ...
متن کامل