Iterated learning and the evolution of language.
By Simon Kirby, Tom Griffiths, Kenny Smith. 2014
326 citations recorded by the source corpus.
Subfields: Cultural Studies, Language and Linguistics
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Cultural Studies
- Nando de Freitas
- Dhruv Batra
- Yucheng Lu
- Aaron C. Courville
- Caglar Gulcehre
- Igor Mordatch
- Orhan Firat
- Jon Gauthier
In Language and Linguistics
Citations in the corpus
- A Paradigm for Situated and Goal-Driven Language Learning (2016, background): “2 A related line of work in evolutionary linguistics constructs a similar language learning scenario entirely without fixed-language agents (Smith et al., 2003; Steels, 2012; Kirby et al., 2014).”
- Natural Language Does Not Emerge ‘Naturally’ in Multi-Agent Dialog (2017, background): “An alternative paradigm that has a long history (Winograd, 1971; Kirby et al., 2014) and is witnessing a recent resurgence (Wang et al., 2016; Fo-erster et al., 2016; Sukhbaatar et al., 2016; Jorge et al., 2016; Lazaridou et al., 2017; Havrylov and Titov, 2017; Mordatch and Abbeel, 2017; Das et…”
- Iterated learning for emergent systematicity in VQA (2021, background): “Originating in cognitive science, IL explains how language evolves to become more compositional and easier-to-acquire in a repeated transmission process, where each new generation acquires the previous generation’s language through a limited number of samples (Kirby et al., 2014).”
- Reinforced Self-Training (ReST) for Language Modeling (2023, background): “Iterated Learning (IL) IL is the process where an agent learns its behavior by being exposed to another agent’s behavior, which itself learned it in the same way (Kirby et al., 2014).”
- When LLMs Play the Telephone Game: Cultural Attractors as Conceptual Tools to Evaluate LLMs in Multi-turn Settings (2024, unknown): “Iterated Learning Parallel works ((Ren et al., 2024; Zhu and Griffiths, 2024)) have studied similar questions using different methodologies, namely the framework of Bayesian Iterated Learning (BIL) ((Kirby et al., 2014; Griffiths and Kalish, 2007)).”