Efficiently Executing Information-Gathering Plans
Proceedings of the Fifteenth International Joint Conference on Artificial Intelligence. Information Retrieval. Pages 785-790.
Abstract
We describe Razor, a planning-based information-gathering agent that assists users by automatically determining which Internet information sites are relevant to their query, accessing those sites in parallel, and integrating the results. Razor uses a disjunctive graphbased plan representation. It then uses a novel and powerful form of local completeness reasoning in order to transform those plans into contingent plans of high quality. These contingent plans can be efficiently executed, obtaining more answers at less cost than the original plans. We focus in this paper on the algorithms underlying the plan transformation process.
@inproceedings{ijcai1997p114,
title = {Efficiently Executing Information-Gathering Plans},
author = {Friedman, Marc T. and Weld, Daniel S.},
booktitle = {Proceedings of the Fifteenth International Joint Conference on
Artificial Intelligence, {IJCAI-97}},
publisher = {International Joint Conferences on Artificial Intelligence},
editor = {Martha E. Pollack},
pages = {785--790},
year = {1997},
note = {Information Retrieval},
url = {https://ijcai.org/proceedings/1997/114},
}
TY - CPAPER TI - Efficiently Executing Information-Gathering Plans AU - Friedman, Marc T. AU - Weld, Daniel S. T2 - Proceedings of the Fifteenth International Joint Conference on Artificial Intelligence, IJCAI-97 PB - International Joint Conferences on Artificial Intelligence PY - 1997 SP - 785 EP - 790 UR - https://ijcai.org/proceedings/1997/114 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
