KitcheNette: Predicting and Recommending Food Ingredient Pairings using Siamese Neural Networks
This work addresses the challenge of identifying optimal and novel food ingredient combinations for chefs and food researchers, though it is incremental as it applies existing neural network techniques to a specific domain.
The authors tackled the problem of predicting and recommending food ingredient pairings by proposing KitcheNette, a model using Siamese neural networks trained on 300K annotated pairing scores, which outperformed baseline models and enabled the discovery of novel pairings.
As a vast number of ingredients exist in the culinary world, there are countless food ingredient pairings, but only a small number of pairings have been adopted by chefs and studied by food researchers. In this work, we propose KitcheNette which is a model that predicts food ingredient pairing scores and recommends optimal ingredient pairings. KitcheNette employs Siamese neural networks and is trained on our annotated dataset containing 300K scores of pairings generated from numerous ingredients in food recipes. As the results demonstrate, our model not only outperforms other baseline models but also can recommend complementary food pairings and discover novel ingredient pairings.