Situated Learning through the Use of Language Games

Abstract

Grammatical agreement is one of the most puzzling aspects found in natural language. Its acquisition requires intensive linguistic exposure and capacities to deal with outliers that break regular patterns. Other than relying on statistical methods to deal with agreement in a computational application, this paper demonstrates how agreement can be learned by artificial agents in a simulated environment in such a way that the openendedness of natural language can be captured by their language processing mechanisms.

Journal: Proceedings of the 19th Annual Machine Learning Conference of Belgium and The Netherlands