Compositional properties of emergent languages in deep learning

• Main Authors: Keresztury, Bence, Bruni, Elia
• Format: Journal Article
• Language: English
• Published: 23-01-2020
• Subjects: Computer Science - Artificial Intelligence; Computer Science - Learning; Statistics - Machine Learning
• DOI: 10.48550/arxiv.2001.08618

Recent findings in multi-agent deep learning systems point towards the
emergence of compositional languages. These claims are often made without exact
analysis or testing of the language. In this work, we analyze the emergent
language resulting from two different cooperative multi-agent game with more
exact measures for compositionality. Our findings suggest that solutions found
by deep learning models are often lacking the ability to reason on an abstract
level therefore failing to generalize the learned knowledge to out of the
training distribution examples. Strategies for testing compositional capacities
and emergence of human-level concepts are discussed.