Emergence of Compositional Language with Deep Generational Transmission

Abstract

Recent work has studied the emergence of language among deep reinforcement learning agents that must collaborate to solve a task. Of particular interest are the factors that cause language to be compositional -- i.e., express meaning by combining words which themselves have meaning. Evolutionary linguists have found that in addition to structural priors like those already studied in deep learning, the dynamics of transmitting language from generation to generation contribute significantly to the emergence of compositionality. In this paper, we introduce these cultural evolutionary dynamics into language emergence by periodically replacing agents in a population to create a knowledge gap, implicitly inducing cultural transmission of language. We show that this implicit cultural transmission encourages the resulting languages to exhibit better compositional generalization.

References in corpus (13)

• Neural Machine Translation by Jointly Learning to Align and Translate
• VQA: Visual Question Answering
• Learning to Communicate with Deep Multi-Agent Reinforcement Learning
• How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation
• Emergence of Grounded Compositional Language in Multi-Agent Populations
• Knowledge Matters: Importance of Prior Information for Optimization
• Multi-Agent Cooperation and the Emergence of (Natural) Language
• Compositional Obverter Communication Learning From Raw Visual Input
• Emergent Translation in Multi-Agent Communication
• Generative Models of Visually Grounded Imagination
• Virtual Embodiment: A Scalable Long-Term Strategy for Artificial Intelligence Research
• Evolving Culture vs Local Minima
• A Paradigm for Situated and Goal-Driven Language Learning

Cited by in corpus (16)

• Compositional Languages Emerge in a Neural Iterated Learning Model
• On the interaction between supervision and self-play in emergent communication
• Towards More Human-like AI Communication: A Review of Emergent Communication Research
• Towards Emergent Language Symbolic Semantic Segmentation and Model Interpretability
• Countering Language Drift with Seeded Iterated Learning
• Dynamic population-based meta-learning for multi-agent communication with natural language
• Low-Bandwidth Communication Emerges Naturally in Multi-Agent Learning Systems
• Inductive Bias and Language Expressivity in Emergent Communication
• Catalytic Role Of Noise And Necessity Of Inductive Biases In The Emergence Of Compositional Communication
• Modeling Conceptual Understanding in Image Reference Games
• Multi-label Iterated Learning for Image Classification with Label Ambiguity
• Symbolic Semantic Segmentation and Interpretation of COVID-19 Lung Infections in Chest CT volumes based on Emergent Languages
• Iterated learning for emergent systematicity in VQA
• Compositionality Through Language Transmission, using Artificial Neural Networks
• Understanding and Enhancing the Use of Context for Machine Translation
• The Emergence of the Shape Bias Results from Communicative Efficiency