Explaining Creative Artifacts

TL;DR

This paper introduces a novel inverse problem approach using a traveling salesman formulation to interpret computational creative artifacts by decomposing them into associative chains, providing insights into the creative process.

Contribution

It presents a new method for post-hoc interpretation of computational creativity outputs by modeling them as traveling salesman problems on knowledge graphs.

Findings

Successfully explained culinary creativity examples.

Extracted explicit concepts from language generation models.

Proposed path length as a measure of creativity novelty.

Abstract

Human creativity is often described as the mental process of combining associative elements into a new form, but emerging computational creativity algorithms may not operate in this manner. Here we develop an inverse problem formulation to deconstruct the products of combinatorial and compositional creativity into associative chains as a form of post-hoc interpretation that matches the human creative process. In particular, our formulation is structured as solving a traveling salesman problem through a knowledge graph of associative elements. We demonstrate our approach using an example in explaining culinary computational creativity where there is an explicit semantic structure, and two examples in language generation where we either extract explicit concepts that map to a knowledge graph or we consider distances in a word embedding space. We close by casting the length of an optimal traveling salesman path as a measure of novelty in creativity.