The Grammar of Emergent Languages

Oskar van der Wal, Silvan de Boer, Elia Bruni, Dieuwke Hupkes


Abstract
In this paper, we consider the syntactic properties of languages emerged in referential games, using unsupervised grammar induction (UGI) techniques originally designed to analyse natural language. We show that the considered UGI techniques are appropriate to analyse emergent languages and we then study if the languages that emerge in a typical referential game setup exhibit syntactic structure, and to what extent this depends on the maximum message length and number of symbols that the agents are allowed to use. Our experiments demonstrate that a certain message length and vocabulary size are required for structure to emerge, but they also illustrate that more sophisticated game scenarios are required to obtain syntactic properties more akin to those observed in human language. We argue that UGI techniques should be part of the standard toolkit for analysing emergent languages and release a comprehensive library to facilitate such analysis for future researchers.
Anthology ID:
2020.emnlp-main.270
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3339–3359
Language:
URL:
https://aclanthology.org/2020.emnlp-main.270
DOI:
10.18653/v1/2020.emnlp-main.270
Bibkey:
Cite (ACL):
Oskar van der Wal, Silvan de Boer, Elia Bruni, and Dieuwke Hupkes. 2020. The Grammar of Emergent Languages. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 3339–3359, Online. Association for Computational Linguistics.
Cite (Informal):
The Grammar of Emergent Languages (van der Wal et al., EMNLP 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/update-css-js/2020.emnlp-main.270.pdf
Video:
 https://slideslive.com/38938733
Code
 i-machine-think/emergent_grammar_induction