The Emergence of Compositional Languages for Numeric Concepts Through Iterated Learning in Neural Agents
Shangmin Guo Yi Ren Serhii Havrylov Stella Frank Ivan Titov Kenny Smith University of Edinburgh
Abstract
Since first introduced by [6], computer simulation has been an increasingly important tool in evolutionary linguistics. Recently, with the development of deep learning techniques, research in grounded language learning has also started to focus on facilitating the emergence of compositional languages without pre-defined elementary linguistic knowledge. In this work, we explore the emergence of compositional languages for numeric concepts in multi-agent communication systems. We demonstrate that compositional language for encoding numeric concepts can emerge through iterated learning in populations of deep neural network agents. However, language properties greatly depend on the input representations given to agents. We found that compositional languages only emerge if they require less iterations to be fully learnt than other non-degenerate languages for agents on a given input representation.
中文速览
多智能体通信系统中能否自发涌现出有组织结构的数字语言，是一个尚未被深入探索的问题。研究者设计了一个名为"Bag-Select"的指称游戏，让深度神经网络智能体通过传递数字概念来完成通信任务，并引入迭代学习（iterated learning）机制——让每一代智能体先从上一代习得语言，再通过交互优化，循环往复地传递给下一代。实验结果表明，在"拼接独热向量"和"场景图像"两种输入表示下，具有组合性（compositionality）的语言确实能从零涌现；而在"集合袋"输入表示下则无法涌现，原因在于该表示下组合性语言并不比其他语言更容易被智能体快速学会。这一发现揭示了一条关键规律：组合性语言之所以能在迭代学习中脱颖而出，是因为它对听者而言比整体性语言学习效率更高，同时也说明输入表示的选择会从根本上影响语言结构的演化，为理解人类语言组合性的起源提供了计算层面的新证据。
原文 arXiv:1910.05291;中英对照 + 大白话阅读 https://aha.fim.ai/paper/1910.05291v1