• Corpus ID: 1227324

Application-Embedded Retrieval from Distributed Free-Text Collections

@inproceedings{Kulyukin1999ApplicationEmbeddedRF,
  title={Application-Embedded Retrieval from Distributed Free-Text Collections},
  author={Vladimir A. Kulyukin},
  booktitle={AAAI/IAAI},
  year={1999}
}
  • V. Kulyukin
  • Published in AAAI/IAAI 18 July 1999
  • Computer Science
A framework is presented for application-embedded information retrieval from distributed free-text collections. An application's usage is sampled by an embedded information retrieval system. Samples are converted into queries to distributed collections. Retrieval is adjusted through sample size and structure, anydata indexing, and dual space feedback. The framework is investigated with a retrieval system embedded in a text processor. 

Figures from this paper

Looking for a haystack: selecting data sources in a distributed retrieval system
TLDR
This dissertation develops a framework for automatic selection of search engines by examining the collection underlying each search engine to determine how properties such as central topic, size, and degree of focus affect retrieval performance.
Generation For Embedded Information Retrieval
TLDR
A personal information retrieval assistant is a software agent embedded in an application that allows the application in which it is embedded to become part of an infrastructure of distributed information sources.
Information access in context
NWU-EECS-06-14 November 21 st , 2006 Context Transformations for Just-intime Retrieval : Adapting the Watson System to User Needs
TLDR
A novel set of techniques for automatically transforming representations of a user’s context for the purpose of just-in-time information retrieval are described, grounded in the experience gained during pilot deployments of the Watson system.
Personalized Search on the World Wide Web
TLDR
Several important user personalization approaches and techniques developed for the Web search domain are illustrated in this chapter, along with examples of real systems currently being used on the Internet.
Beyond Similarity
TLDR
This work proposes techniques that bring modest amounts of task-specific knowledge to bear in order to perform lexical transformations on the queries these systems perform, thereby ensuring they retrieve not similar documents, but documents that are relevant and useful in purposeful and interesting ways.
Ranked retrieval with semantic networks and vector spaces
TLDR
The equivalence of semantic networks with spreading activation and vector spaces with dot product is investigated under ranked retrieval and it is shown that the two models can be effectively constructed from each other.
Selecting Task-Relevant Sources for Just-in-Time Retrieval
SelectingTask-RelevantSourcesforJust-in-TimeRetrievalDavidB.LeakeandRyanScherleComputerScienceDepartmentIndianaUniversity150S.Wo o dlawnAvenueBlo
Computing point-of-view: modeling and simulating judgments of taste
TLDR
Inspired by cultural theories of taste and identity, this thesis explores end-to-end computational modeling of people's tastes---from model acquisition, to generalization, to application---under various realms.

References

SHOWING 1-10 OF 28 REFERENCES
Question-driven information retrieval systems
TLDR
An approach is presented to building question-driven information retrieval systems to answer natural language questions from collections of free-text question-answer pairs by combining numerical techniques of information retrieval with scalable, knowledge- based approaches of natural language processing.
Real life information retrieval: a study of user queries on the Web
We analyzed transaction logs of a set of 51,473 queries posed by 18,113 users of Excite, a major Internet search service. We provide data on: (i) queries --- the number of search terms, and the use
Incremental relevance feedback
TLDR
This paper focuses on a relevance feedback technique that allows easily understandable and manageable user interfaces, and at the same time provides high-quality retrieval results.
Answering Questions for an Organization Online
TLDR
This work developed an approach to building organization-embedded question-answering intermediaries, called Information Exchange systems, which use their knowledge of the organization's structure to answer the clients' questions and to acquire new expertise from the organizations' experts.
Interaction in information retrieval: selection and effectiveness of search terms
TLDR
Search terms from users' written question statements and term relevance feedback were the most productive sources of terms contributing to the retrieval of items judged relevant by users.
Knowledge-Based Navigation of Complex Information Spaces
TLDR
This work has built several developed an approach to building data "tour guides," called FINDME systems, which have combined ideas of instance-based browsing, structuring retrieval around the critiquing of previously-retrieved examples, and retrieval strategies, knowledge-based heuristics for finding relevant information.
WordNet: A Lexical Database for English
TLDR
WordNet1 provides a more effective combination of traditional lexicographic information and modern computing, and is an online lexical database designed for use under program control.
Introduction to Modern Information Retrieval
TLDR
Reading is a need and a hobby at once and this condition is the on that will make you feel that you must read.
Building embedded conceptual parsers
This dissertation describes how to build conceptual parsers (that is, natural language understanding systems built on semantic and pragmatic principles) that are embedded into application programs. A
An Interactive and Collaborative Approach To Answering Questions for an Organization
TLDR
An emerging World Wide Web application is described, called the Chicago Information Exchange, that manages the online textual expertise of the University of Chicago Computer Science Department and acts as a web-based intermediary between its clients and experts.
...
1
2
3
...