On the Optimality of Discrete Object Naming: a Kinship Case Study

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Le, Phong, Lindeman, Mees, Alhama, Raquel G.
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909920880754688
author Le, Phong
Lindeman, Mees
Alhama, Raquel G.
author_facet Le, Phong
Lindeman, Mees
Alhama, Raquel G.
contents The structure of naming systems in natural languages hinges on a trade-off between high informativeness and low complexity. Prior work capitalizes on information theory to formalize these notions; however, these studies generally rely on two simplifications: (i) optimal listeners, and (ii) universal communicative need across languages. Here, we address these limitations by introducing an information-theoretic framework for discrete object naming systems, and we use it to prove that an optimal trade-off is achievable if and only if the listener's decoder is equivalent to the Bayesian decoder of the speaker. Adopting a referential game setup from emergent communication, and focusing on the semantic domain of kinship, we show that our notion of optimality is not only theoretically achievable but also emerges empirically in learned communication systems.
format Preprint
id arxiv_https___arxiv_org_abs_2511_19120
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle On the Optimality of Discrete Object Naming: a Kinship Case Study
Le, Phong
Lindeman, Mees
Alhama, Raquel G.
Computation and Language
Artificial Intelligence
The structure of naming systems in natural languages hinges on a trade-off between high informativeness and low complexity. Prior work capitalizes on information theory to formalize these notions; however, these studies generally rely on two simplifications: (i) optimal listeners, and (ii) universal communicative need across languages. Here, we address these limitations by introducing an information-theoretic framework for discrete object naming systems, and we use it to prove that an optimal trade-off is achievable if and only if the listener's decoder is equivalent to the Bayesian decoder of the speaker. Adopting a referential game setup from emergent communication, and focusing on the semantic domain of kinship, we show that our notion of optimality is not only theoretically achievable but also emerges empirically in learned communication systems.
title On the Optimality of Discrete Object Naming: a Kinship Case Study
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2511.19120