Proceedings ArticleDOI
IR-NLI II: applying man-machine interaction and artificial intelligence conceptsto information retrieval
Giorgio Brajnik,Giovanni Guida,Carlo Tasso +2 more
- pp 387-399
Reads0
Chats0
TLDR
The overall organization of the IR-NLI II system is presented, together with a short description of the two main modules implemented so far, namely the Information Retrieval Expert Subsystem and the User Modeling Subsystem.Abstract:
This paper addresses the problem of building expert interfaces to information retrieval systems. In particular, the problem of augmenting the capabilities of such interfaces with user modeling features is discussed and the main benefits of this approach are outlined. The paper presents a prototype system called IR-NLI II, devoted to model by means of artificial intelligence techniques the human intermediary to information retrieval systems. The overall organization of the IR-NLI II system is presented, together with a short description of the two main modules implemented so far, namely the Information Retrieval Expert Subsystem and the User Modeling Subsystem. An example of interaction with IR-NLI II is described. Perspectives and future research directions are finally outlined.read more
Citations
More filters
Journal ArticleDOI
Machine learning for information retrieval: neural networks, symbolic learning, and genetic algorithms
TL;DR: This article presents three popular methods: the connectionist Hopfield network; the symbolic ID3/ID5R; and evolution-based genetic algorithms, which are promising in their ability to analyze user queries, identify users' information needs, and suggest alternatives for search.
Journal ArticleDOI
User modeling in expert man-machine interfaces: a case study in intelligent information retrieval
TL;DR: The authors focus on a knowledge-based system, called UM-tool, devoted to creating, maintaining, and using explicit user models within an expert interface, which supports a novel approach to user modeling.
Journal ArticleDOI
An expert system for automatic query reformation
Susan Gauch,John B. Smith +1 more
TL;DR: An expert system for online search assistance automatically reformulates queries to improve the search results, and ranks the retrieved passages to speed the identification of relevant information.
Journal ArticleDOI
Search improvement via automatic query reformulation
Susan Gauch,John B. Smith +1 more
TL;DR: This prototype augments the searching capabilities of novice users by providing automatic query reformulation to improve the search results, and automatic ranking of the retrieved passages to speed the identification of relevant information.
Journal ArticleDOI
Interaction in information retrieval: trends over time
TL;DR: This review examines a sample of interactive information retrieval systems within the framework of a design challenge set forth by John Bennett in 1971 to characterize interactive IR design trends over time, examine the extent to which IR systems have responded to Bennett's design challenge, and suggest potential future research directions and challenges.
References
More filters
Journal ArticleDOI
Users are individuals
TL;DR: This article presents some situations in which individual user models are important and some techniques that make the construction and use of such models possible and the performance of one system that uses some of these techniques is discussed.
Book
Information search tactics
TL;DR: In this paper, the concept of the search tactic, or move made to further a search, is introduced, and twenty-nine search tactics are discussed in four categories: monitoring, file structure, search formulation, and term.
Journal ArticleDOI
Information search tactics
TL;DR: The concept of the search tactic, or move made to further a search, is introduced and twenty-nine tactics are named, defined, and discussed in four categories: monitoring, file structure, search formulation, and term.
Journal ArticleDOI
Information retrieval through man‐machine dialogue
TL;DR: Initial tests with a prototype program indicate that a performance equal to that obtainable from a more conventional on‐line retrieval system is possible without obliging the user to formulate his query.