Towards Fine-Dining Recipe Generation with Generative Pre-trained Transformers

All recipes, no matter their contents and level of difficulty, follow a certain structure to an extend. It includes the recipe name, the ingredients and the instructions. All the recipes we will use will include this information. On top of that, recipes can be seen as a sequence of characters which makes them great inputs to characterlevel Recurrent neural networks as well as autoregressive models like the GPT-2 transformer. We would like to train the models on existing recipes and then have them recommend brand new ones. In the following experiments, we will make use of a transformer, more specifically a pre-trained GPT-2 model in order to generate structured recipes from scratch. For all this, we are going to be using a brand new dataset we created, from publicly available data. The novel dataset we create features specifically "fine-dining" recipes and the model is specifically fine-tuned to generate "gourmet" dishes unlike all the previous "normal" recipe models.