Inductive Bias and Language Expressivity in Emergent Communication

Abstract

Referential games and reconstruction games are the most common game types for studying emergent languages. We investigate how the type of the language game affects the emergent language in terms of: i) language compositionality and ii) transfer of an emergent language to a task different from its origin, which we refer to as language expressivity. With empirical experiments on a handcrafted symbolic dataset, we show that languages emerged from different games have different compositionality and further different expressivity.

References in corpus (10)

• Adam: A Method for Stochastic Optimization
• Categorical Reparameterization with Gumbel-Softmax
• Grounded Language Learning in a Simulated 3D World
• Multi-Agent Cooperation and the Emergence of (Natural) Language
• Language Understanding for Text-based Games Using Deep Reinforcement Learning
• Compositional Languages Emerge in a Neural Iterated Learning Model
• Emergence of Compositional Language with Deep Generational Transmission
• Measuring Compositionality in Representation Learning
• The Emergence of Compositional Languages for Numeric Concepts Through Iterated Learning in Neural Agents
• Emergence of Numeric Concepts in Multi-Agent Autonomous Communication

Cited by in corpus (4)

• Emergent Language: A Survey and Taxonomy
• Learning to Draw: Emergent Communication through Sketching
• Catalytic Role Of Noise And Necessity Of Inductive Biases In The Emergence Of Compositional Communication
• Structural Inductive Biases in Emergent Communication