Compositionality has traditionally been understood as a major factor in productivity of language and, more broadly, human cognition. Yet, recently, some research started to question its status, showing that artificial neural networks are good at generalization even without noticeable compositional behavior. We argue that some of these conclusions are too strong and/or incomplete. In the context of a two-agent communication game, we show that compositionality indeed seems essential for successful generalization when the evaluation is done on a proper dataset.
View on arXiv