Experimentally Evaluating Communicative Strategies: The Effect of the Task
Abstract
Effective problem solving among multiple agents requires a better understanding of the role of communication in collaboration. In this paper we show that there are communicative strategies that greatly improve the performance of resource-bounded agents, but that these strategies are highly sensitive to the task requirements, situation parameters and agents' resource limitations. We base our argument on two sources of evidence: (1) an analysis of a corpus of 55 problem solving dialogues, and (2) experimental simulations of collaborative problem solving dialogues in an experimental world, Design-World, where we parameterize task requirements, agents' resources and communicative strategies.
Cite
Text
Walker. "Experimentally Evaluating Communicative Strategies: The Effect of the Task." AAAI Conference on Artificial Intelligence, 1994. doi:10.48550/arxiv.cmp-lg/9408015Markdown
[Walker. "Experimentally Evaluating Communicative Strategies: The Effect of the Task." AAAI Conference on Artificial Intelligence, 1994.](https://mlanthology.org/aaai/1994/walker1994aaai-experimentally/) doi:10.48550/arxiv.cmp-lg/9408015BibTeX
@inproceedings{walker1994aaai-experimentally,
title = {{Experimentally Evaluating Communicative Strategies: The Effect of the Task}},
author = {Walker, Marilyn A.},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {1994},
pages = {86-93},
doi = {10.48550/arxiv.cmp-lg/9408015},
url = {https://mlanthology.org/aaai/1994/walker1994aaai-experimentally/}
}