Modelling type-denoting concepts and words in a simulation of vocabulary development.
Luc Steels proposes a mechanism by which a community of agents is able to negotiate a common vocabulary for referring to objects in their environment, using two simple games. In a ‘discrimination game’, an agent equipped with a set of simple sensory channels attempts to distinguish a target from a set of context objects. If it cannot do so, it subdivides one of its channels to make discrimination more likely in future. In a ‘language game’, a speaker agent identifies an object in the world, and consults a lexicon of mappings from object concepts to words to generate a word for this object, that is then passed to a hearer agent. The hearer uses its own lexicon to attempt to identify the object in question. If successful, the word-concept mapping is reinforced for both speaker and hearer; if not, the speaker indicates the intended object explicitly. Using these games, a group of agents can successfully develop a shared vocabulary. However, it is possible that the success of Steels’ system is an artifact of the highly artificial classification and word-learning mechanisms which agents use. Discrimination games make no reference to current biological theories of perception and discrimination, and language games make no reference to psychological theories of vocabulary acquisition. This thesis describes a Steels-like system in which agents have more psychologically realistic categorisation and word-learning methods. The main conclusion of this work is that Steels’ system can be successfully reimplemented using more psycho- logically realistic object classification and word-learning methods.
Advisor: Knott, Alistair; McCallum, Simon
Degree Name: Master of Science
Degree Discipline: Computer Science
Publisher: University of Otago
Research Type: Thesis