Rodríguez Luna, DianaPonti, Edoardo MariaHupkes, DieuwkeBruni, Elia2024-06-252024-06-252020Rodríguez D, Ponti EM, Hupkes D, Bruni E. Internal and external pressures on language emergence: least effort, object constancy and frequency. In: Cohn T, He Y, Liu Y, editors. Findings of the Association for Computational Linguistics: EMNLP 2020; 2020 Nov 16-20; [Kerrville, Texas]. Stroudsburg (PA): Association for Computational Linguistics; 2020. p. 4428-37. DOI: 10.18653/v1/2020.findings-emnlp.397978-1-952148-90-3http://hdl.handle.net/10230/60576Comunicació presentada al The 2020 Conference on Empirical Methods in Natural LanguageIn previous work, artificial agents were shown to achieve almost perfect accuracy in referential games where they have to communicate to identify images. Nevertheless, the resulting communication protocols rarely display salient features of natural languages, such as compositionality. In this paper, we propose some realistic sources of pressure on communication that avert this outcome. More specifically, we formalise the principle of least effort through an auxiliary objective. Moreover, we explore several game variants, inspired by the principle of object constancy, in which we alter the frequency, position, and luminosity of the objects in the images. We perform an extensive analysis on their effect through compositionality metrics, diagnostic classifiers, and zero-shot evaluation. Our findings reveal that the proposed sources of pressure result in emerging languages with less redundancy, more focus on high-level conceptual information, and better abilities of generalisation. Overall, our contributions reduce the gap between emergent and natural languages.application/pdfengACL materials are Copyright © 1963–2024 ACL; other materials are copyrighted by their respective copyright holders. Materials prior to 2016 here are licensed under the Creative Commons Attribution-NonCommercial-ShareAlike 3.0 International License. Permission is granted to make copies for the purposes of teaching and research. Materials published in or after 2016 are licensed on a Creative Commons Attribution 4.0 International License.ComunicacióTractament del llenguatge natural (Informàtica)Sistema mètricinfo:eu-repo/semantics/conferenceObjecthttp://dx.doi.org/10.18653/v1/2020.findings-emnlp.397info:eu-repo/semantics/openAccess