Our simulations show that neural agents mainly strive to maintain the utterance type distribution observed during learning, instead of developing a more ...
Apr 15, 2021 · Abstract: Natural languages commonly display a trade-off among different strategies to convey constituent roles. A similar trade-off, ...
The authors' simulations of iterated language learning with neural network agents show that neural agents mainly strive to maintain the utterance type ...
Lian, Y.; Bisazza, A.; Verhoef, T. (2021). The effect of efficient messaging and input variability on neural-agent iterated language learning.
Our simulations show that neural agents mainly strive to maintain the utterance type distribution observed during learning, instead of developing a more ...
On-demand video platform giving you access to lectures from conferences worldwide.
TL;DR: This article showed that neural agents mainly strive to maintain the utterance type distribution observed during learning, instead of developing a ...
On-demand video platform giving you access to lectures from conferences worldwide.
The Effect of Efficient Messaging and Input Variability on Neural-Agent Iterated Language Learning. Lian, Y., Bisazza, A., & Verhoef, T. In Empirical ...
In this work, we re-evaluate this result in the light of two important factors, namely: the lack of effort-based pressure in the agents and the lack of ...