A Compositional Explanation of the Pet Fish Phenomenon
Bob Coecke, Martha Lewis

TL;DR
This paper demonstrates how a compositional distributional model can naturally explain the pet fish phenomenon, showing that concept interactions via grammatical roles account for non-compositional effects.
Contribution
It introduces a formal compositional model that explains the pet fish phenomenon, bridging the gap between non-compositionality and compositional semantics.
Findings
The model accounts for pet fish phenomenon in illustrative examples.
Application to experimental data supports the model's validity.
Discussion of potential extensions enhances the formalism's scope.
Abstract
The `pet fish' phenomenon is often cited as a paradigm example of the `non-compositionality' of human concept use. We show here how this phenomenon is naturally accommodated within a compositional distributional model of meaning. This model describes the meaning of a composite concept by accounting for interaction between its constituents via their grammatical roles. We give two illustrative examples to show how the qualitative phenomena are exhibited. We go on to apply the model to experimental data, and finally discuss extensions of the formalism.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
