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

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Lee, Hyoyeon, Bullock, Seth, Houghton, Conor
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911356538585088
author Lee, Hyoyeon
Bullock, Seth
Houghton, Conor
author_facet Lee, Hyoyeon
Bullock, Seth
Houghton, Conor
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2601_02911
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Image, Word and Thought: A More Challenging Language Task for the Iterated Learning Model
Lee, Hyoyeon
Bullock, Seth
Houghton, Conor
Computation and Language
Machine Learning
Multiagent Systems
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.
title Image, Word and Thought: A More Challenging Language Task for the Iterated Learning Model
topic Computation and Language
Machine Learning
Multiagent Systems
url https://arxiv.org/abs/2601.02911