< Back to previous page

Publication

Situated Learning through the Use of Language Games

Book Contribution - Book Chapter Conference Contribution

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 articial agents in a simulated environment in such a way that the open-endedness of natural language can be captured by their language processing mechanisms.
Book: Proceedings of the 19th Annual Machine Learning Conference of Belgium and The Netherlands
Series: Proceedings of the 19th Annual Machine Learning Conference of Belgium and The Netherlands
Keywords:language games, machine learning, Hungarian
  • ORCID: /0000-0003-4451-4778/work/61182923