Studies of discrete languages emerging when
neural agents communicate to solve a joint
task often look for evidence of compositional
structure. This stems for the expectation that
such a structure would allow languages to be
acquired faster by the agents and enable them
to generalize better. We argue that these beneficial properties are only loosely connected
to compositionality. In two experiments, we
demonstrate that, depending on the task, noncompositional languages might show equal, or
better, ...
Studies of discrete languages emerging when
neural agents communicate to solve a joint
task often look for evidence of compositional
structure. This stems for the expectation that
such a structure would allow languages to be
acquired faster by the agents and enable them
to generalize better. We argue that these beneficial properties are only loosely connected
to compositionality. In two experiments, we
demonstrate that, depending on the task, noncompositional languages might show equal, or
better, generalization performance and acquisition speed than compositional ones. Further
research in the area should be clearer about
what benefits are expected from compositionality, and how the latter would lead to them.
+
