NeurIPS 2019poster144 citations
Anti-efficient encoding in emergent communication
Rahma Chaabouni, Eugene Kharitonov, Emmanuel Dupoux, Marco Baroni
Abstract
Despite renewed interest in emergent language simulations with neural networks, little is known about the basic properties of the induced code, and how they compare to human language. One fundamental characteristic of the latter, known as Zipf's Law of Abbreviation (ZLA), is that more frequent words are efficiently associated to shorter strings. We study whether the same pattern emerges when two neural networks, a
BibTeX
@inproceedings{NEURIPS2019_31ca0ca7,
author = {Chaabouni, Rahma and Kharitonov, Eugene and Dupoux, Emmanuel and Baroni, Marco},
booktitle = {Advances in Neural Information Processing Systems},
editor = {H. Wallach and H. Larochelle and A. Beygelzimer and F. d\textquotesingle Alch\'{e}-Buc and E. Fox and R. Garnett},
pages = {},
publisher = {Curran Associates, Inc.},
title = {Anti-efficient encoding in emergent communication},
url = {https://proceedings.neurips.cc/paper_files/paper/2019/file/31ca0ca71184bbdb3de7b20a51e88e90-Paper.pdf},
volume = {32},
year = {2019}
}