Intelligent clustering as source of knowledge for web dialogue manager in a information retrieval system

Authors:
Paulo Quaresma;Irene Pimenta Rodrigues
Affiliations:
Departamento de Informática, Universidade de Évora, Largo dos Colegiais, 7000 Évora, Portugal;Departamento de Informática, Universidade de Évora, Largo dos Colegiais, 7000 Évora, Portugal
Venue:
Intelligent exploration of the web
Year:
2003

Citing 11
Cited 0

Attention, intentions, and the structure of discourse

Computational Linguistics
Automatic text processing: the transformation, analysis, and retrieval of information by computer

Automatic text processing: the transformation, analysis, and retrieval of information by computer
Scatter/Gather: a cluster-based approach to browsing large document collections

SIGIR '92 Proceedings of the 15th annual international ACM SIGIR conference on Research and development in information retrieval
Constant interaction-time scatter/gather browsing of very large document collections

SIGIR '93 Proceedings of the 16th annual international ACM SIGIR conference on Research and development in information retrieval
The repair of speech act misunderstandings by abductive inference

Computational Linguistics
Collaborative plans for complex group action

Artificial Intelligence
Reexamining the cluster hypothesis: scatter/gather on retrieval results

SIGIR '96 Proceedings of the 19th annual international ACM SIGIR conference on Research and development in information retrieval
Planning text for advisory dialogues: capturing intentional and rhetorical information

Computational Linguistics
Collaborative response generation in planning dialogues

Computational Linguistics - Special issue on natural language generation
A collaborative planning model of intentional structure

Computational Linguistics
A process model for recognizing communicative acts and modeling negotiation subdialogues

Computational Linguistics

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present an dialogue manager for a Web information retrieval system that uses intelligent clustering techniques in order to be more cooperative. The proposed system provides an intelligent behavior during user interactions through the use of domain knowledge and the construction of an interaction context. Domain Knowledge is used to build clusters of documents which are presented to the users as graph structure and as choice menus. The interaction context is used to allow the system to interpret a new query in the context of the previous interactions. We present a detailed example of an interaction with the proposed system.