Existing approaches to recipe generation are unable to create recipes for users with culinary preferences but incomplete knowledge of ingredients in specific dishes. We propose a new task of personalized recipe generation to help these users: expanding a name and incomplete ingredient details into complete natural-text instructions aligned with the user's historical preferences. We attend on technique- and recipe-level representations of a user's previously consumed recipes, fusing these 'user-aware' representations in an attention fusion layer to control recipe text generation. Experiments on a new dataset of 180K recipes and 700K interactions show our model's ability to generate plausible and personalized recipes compared to non-personalized baselines.
@article{arxiv.1909.00105,
title = {Generating Personalized Recipes from Historical User Preferences},
author = {Bodhisattwa Prasad Majumder and Shuyang Li and Jianmo Ni and Julian McAuley},
journal= {arXiv preprint arXiv:1909.00105},
year = {2019}
}
Comments
Accepted in EMNLP 2019. Data and codes are available at https://github.com/majumderb/recipe-personalization