| Bookmark: |
Full-text
| URL: http://www.isrl.uiuc.edu/~gasser/papers/...lity-evolang2008.pdf |
| Cached: PDF-154K |
| SAVE AS an easy-to-recall long filename: |
| Filename format: author--year--title PDF-154K |
| Filename format: author--year--title--journal|proceedings|...--pages PDF-154K |
Related links
| Web search: Google Web Search :: Google Scholar |
| Within this site: References (7) |
Abstract
We show that artificial language evolution involves the interplay of two opposing forces: pres- sure toward simple representations imposed by the dynamics of collective learning, and pres- sure towards complex representations imposed by requirements of agents tasks. The push-pull of these two forces results in the emergence of a language that is balanced: simple but not too simple. We introduce the classification game to study the emergence of these balanced languages and their properties. Our agents use artificial neural networks to learn how to solve tasks, and a simple counting algorithm to simultaneously learn a language as a form-meaning mapping. We show that task-language coupling drives the simplicity-complexity balance, and that both compositional and holistic languages can emerge.BibTex
@incollection{swarup08evolang7th,
author={Samarth Swarup and Les Gasser},
title={Simple, but not too Simple: Learnability vs. Functionality in Language Evolution},
year={2008},
month={March},
pages={299-306},
editor={A. D. M. Smith and K. Smith and R. Ferrer-i-Cancho},
publisher={World Scientific},
booktitle={Proceedings of the 7th International Conference on the Evolution of Language},
url={http://www.isrl.uiuc.edu/~amag/langev/paper/swarup08evolang7th.html}
}
| HOME :: Edited Book List :: Book Chapter | Comments to: junwang4 you-know-at gmail.com | Last update: 10/27/09 |