Go to ACL ARR 2024 December homepageSearching for the Most Human-like Emergent Language
Abstract: In this paper, we design a signalling game-based emergent communication environment to generate state-of-the-art emergent languages in terms of similarity to human language. This is done with hyperparameter optimization, using XferBench as the objective function. XferBench quantifies the statistical similarity of emergent language to human language by measuring its suitability for deep transfer learning to human language. Additionally, we demonstrate the predictive power of entropy on the transfer learning performance of an emergent language as well as validate previous results on the entropy-minimization properties of emergent communication systems. Finally, we report generalizations regarding what hyperparameters produce more realistic emergent languages, that is, ones which transfer better to human language.
Paper Type: Long
Research Area: Machine Learning for NLP
Research Area Keywords: transfer learning / domain adaptation, reinforcement learning
Contribution Types: Model analysis & interpretability, Publicly available software and/or pre-trained models
Languages Studied: AI-invented
Submission Number: 449
Loading