Image, Word and Thought: A More Challenging Language Task for the Iterated Learning Model

TL;DR

This paper extends the iterated learning model to complex visual meanings, demonstrating that agents can develop expressive, compositional, and stable languages for seven-segment display images, advancing understanding of language emergence.

Contribution

It introduces a semi-supervised iterated learning model applied to complex visual meanings, showing successful language transmission with larger meaning-signal spaces.

Findings

Agents learned and transmitted expressive languages for 128 glyphs

Languages were compositional with consistent mappings

Languages remained stable across generations

Abstract

The iterated learning model simulates the transmission of language from generation to generation in order to explore how the constraints imposed by language transmission facilitate the emergence of language structure. Despite each modelled language learner starting from a blank slate, the presence of a bottleneck limiting the number of utterances to which the learner is exposed can lead to the emergence of language that lacks ambiguity, is governed by grammatical rules, and is consistent over successive generations, that is, one that is expressive, compositional and stable. The recent introduction of a more computationally tractable and ecologically valid semi supervised iterated learning model, combining supervised and unsupervised learning within an autoencoder architecture, has enabled exploration of language transmission dynamics for much larger meaning-signal spaces. Here, for the first time, the model has been successfully applied to a language learning task involving the communication of much more complex meanings: seven-segment display images. Agents in this model are able to learn and transmit a language that is expressive: distinct codes are employed for all 128 glyphs; compositional: signal components consistently map to meaning components, and stable: the language does not change from generation to generation.