2023/05/22 by Emily Cheng, Cheng, Emily, Mathieu Rita +3
Computer Science · Social Sciences · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Language and cultural evolution #Natural Language Processing Techniques #Neural and Evolutionary Computing (cs.NE) #Speech and dialogue systems
paper · pdf · doi:10.48550/arxiv.2305.12941
openalex publication_date 2023/05/22 · openalex created_date 2023/05/24 · openalex updated_date 2026/07/28
Compositionality is a hallmark of human language that not only enables linguistic generalization, but also potentially facilitates acquisition. When simulating language emergence with neural networks, compositionality has been shown to improve communication performance; however, its impact on imitation learning has yet to be investigated. Our work explores the link between compositionality and imitation in a Lewis game played by deep neural agents. Our contributions are twofold: first, we show that the learning algorithm used to imitate is crucial: supervised learning tends to produce more average languages, while reinforcement learning introduces a selection pressure toward more compositional languages. Second, our study reveals that compositional languages are easier to imitate, which may induce the pressure toward compositional languages in RL imitation settings.