RecipeMind: Guiding Ingredient Choices from Food Pairing to Recipe Completion using Cascaded Set Transformer

Abstract

We propose a computational approach for recipe ideation, a downstream task that helps users select and gather ingredients for creating dishes. To perform this task, we developed RecipeMind, a food anity score prediction model that quanties the suitability of adding an ingredient to set of other ingredients. We constructed a large-scale dataset containing ingredient co-occurrence based scores to train and evaluate RecipeMind on food anity score prediction. Deployed in recipe ideation, RecipeMind helps the user expand an initial set of ingredients by suggesting additional ingredients. Experiments and qualitative analysis show RecipeMind's potential in fullling its assistive role in cuisine domain.