Searching for the Most Human-like Emergent Language
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916988055453696 |
|---|---|
| author | Boldt, Brendon Mortensen, David |
| author_facet | Boldt, Brendon Mortensen, David |
| contents | In this paper, we design a signalling game-based emergent communication environment to generate state-of-the-art emergent languages in terms of similarity to human language. This is done with hyperparameter optimization, using XferBench as the objective function. XferBench quantifies the statistical similarity of emergent language to human language by measuring its suitability for deep transfer learning to human language. Additionally, we demonstrate the predictive power of entropy on the transfer learning performance of emergent language as well as corroborate previous results on the entropy-minimization properties of emergent communication systems. Finally, we report generalizations regarding what hyperparameters produce more realistic emergent languages, that is, ones which transfer better to human language. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_03467 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Searching for the Most Human-like Emergent Language Boldt, Brendon Mortensen, David Computation and Language I.2.7; I.6.m In this paper, we design a signalling game-based emergent communication environment to generate state-of-the-art emergent languages in terms of similarity to human language. This is done with hyperparameter optimization, using XferBench as the objective function. XferBench quantifies the statistical similarity of emergent language to human language by measuring its suitability for deep transfer learning to human language. Additionally, we demonstrate the predictive power of entropy on the transfer learning performance of emergent language as well as corroborate previous results on the entropy-minimization properties of emergent communication systems. Finally, we report generalizations regarding what hyperparameters produce more realistic emergent languages, that is, ones which transfer better to human language. |
| title | Searching for the Most Human-like Emergent Language |
| topic | Computation and Language I.2.7; I.6.m |
| url | https://arxiv.org/abs/2510.03467 |