@inproceedings{kalocinski_quantifier_2015,
	address = {Richland, SC},
	series = {{AAMAS} '15},
	title = {Quantifier {Learning}: {An} {Agent}-based {Coordination} {Model}},
	isbn = {978-1-4503-3413-6},
	shorttitle = {Quantifier {Learning}},
	url = {http://dl.acm.org/citation.cfm?id=2772879.2773470},
	abstract = {We consider the problem of learning the meaning of natural language expressions. In contrast to traditional settings, in which agents infer prescribed meanings from observations, we focus on an algorithm for the coordination of meaning among many agents. We do not assume any external correctness criterion. We propose an agent-based iterative algorithm for coordinating the semantics of upward monotone proportional quantifiers. We describe simple instances of our model in terms of Markov chains. We observe a mathematical connection between the possibility of convergence and specific levels of agents authority and complexity of communication patterns. We discuss the possibility of extending the model to cover the parameter of spatial separation.},
	urldate = {2015-11-04},
	booktitle = {Proceedings of the 2015 {International} {Conference} on {Autonomous} {Agents} and {Multiagent} {Systems}},
	publisher = {International Foundation for Autonomous Agents and Multiagent Systems},
	author = {Kaloci\'nski, Dariusz and Gierasimczuk, Nina and Mostowski, Marcin},
	year = {2015},
	keywords = {coordination, multi-agent learning, natural language, quantifiers, semantics},
	pages = {1853--1854}
}