SOTAVerified

Generating Personalized Recipes from Historical User Preferences

2019-08-31IJCNLP 2019Code Available0· sign in to hype

Bodhisattwa Prasad Majumder, Shuyang Li, Jianmo Ni, Julian McAuley

Code Available — Be the first to reproduce this paper.

Reproduce

Code

Abstract

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.

Tasks

Benchmark Results

DatasetModelMetricClaimedVerifiedStatus
Food.comPrior NameBLEU-128.05Unverified

Reproductions