The University of Southampton
University of Southampton Institutional Repository

Speaking your language: spatial relationships in interpretable emergent communication

Speaking your language: spatial relationships in interpretable emergent communication
Speaking your language: spatial relationships in interpretable emergent communication
Effective communication requires the ability to refer to specific parts of an observation in relation to others. While emergent communication literature shows success in developing various language properties, no research has shown the emergence of such positional references. This paper demonstrates how agents can communicate about spatial relationships within their observations. The results indicate that agents can develop a language capable of expressing the relationships between parts of their observation, achieving over 90% accuracy when trained in a referential game which requires such communication. Using a collocation measure, we demonstrate how the agents create such references. This analysis suggests that agents use a mixture of non-compositional and compositional messages to convey spatial relationships. We also show that the emergent language is interpretable by humans. The translation accuracy is tested by communicating with the receiver agent, where the receiver achieves over 78% accuracy using parts of this lexicon, confirming that the interpretation of the emergent language was successful.
Lipinski, Olaf
88709b3f-c356-45c7-8520-cb49d7b07960
Sobey, Adam
e850606f-aa79-4c99-8682-2cfffda3cd28
Cerutti, Federico
fec75499-632a-460f-987a-1a09420d8cb1
Norman, Tim
663e522f-807c-4569-9201-dc141c8eb50d
Lipinski, Olaf
88709b3f-c356-45c7-8520-cb49d7b07960
Sobey, Adam
e850606f-aa79-4c99-8682-2cfffda3cd28
Cerutti, Federico
fec75499-632a-460f-987a-1a09420d8cb1
Norman, Tim
663e522f-807c-4569-9201-dc141c8eb50d

Lipinski, Olaf, Sobey, Adam, Cerutti, Federico and Norman, Tim (2024) Speaking your language: spatial relationships in interpretable emergent communication. NeurIPS 2024, Thirty-Eighth Annual Conference on Neural Information Processing Systems, , Vancouver, Canada. 09 - 15 Dec 2024.

Record type: Conference or Workshop Item (Paper)

Abstract

Effective communication requires the ability to refer to specific parts of an observation in relation to others. While emergent communication literature shows success in developing various language properties, no research has shown the emergence of such positional references. This paper demonstrates how agents can communicate about spatial relationships within their observations. The results indicate that agents can develop a language capable of expressing the relationships between parts of their observation, achieving over 90% accuracy when trained in a referential game which requires such communication. Using a collocation measure, we demonstrate how the agents create such references. This analysis suggests that agents use a mixture of non-compositional and compositional messages to convey spatial relationships. We also show that the emergent language is interpretable by humans. The translation accuracy is tested by communicating with the receiver agent, where the receiver achieves over 78% accuracy using parts of this lexicon, confirming that the interpretation of the emergent language was successful.

This record has no associated files available for download.

More information

Accepted/In Press date: 25 September 2024
Published date: December 2024
Venue - Dates: NeurIPS 2024, Thirty-Eighth Annual Conference on Neural Information Processing Systems, , Vancouver, Canada, 2024-12-09 - 2024-12-15

Identifiers

Local EPrints ID: 494648
URI: http://eprints.soton.ac.uk/id/eprint/494648
PURE UUID: 2a0e7e40-185a-4a61-a14a-46dc57605f5f
ORCID for Olaf Lipinski: ORCID iD orcid.org/0000-0002-2023-7617
ORCID for Adam Sobey: ORCID iD orcid.org/0000-0001-6880-8338
ORCID for Tim Norman: ORCID iD orcid.org/0000-0002-6387-4034

Catalogue record

Date deposited: 11 Oct 2024 16:59
Last modified: 12 Oct 2024 02:31

Export record

Contributors

Author: Olaf Lipinski ORCID iD
Author: Adam Sobey ORCID iD
Author: Federico Cerutti
Author: Tim Norman ORCID iD

Download statistics

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of http://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×