English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Over the past two decades, recommendation systems (RSs) have used machinelearning (ML) solutions to recommend items, e.g., movies, books, andrestaurants, to clients of a business or an online platform. Reciperecommendation, however, has not yet received much attention compared to thoseapplications. We introduce RECipe as a multi-purpose recipe recommendationframework with a multi-modal knowledge graph (MMKG) backbone. The motivationbehind RECipe is to go beyond (deep) neural collaborative filtering (NCF) byrecommending recipes to users when they query in natural language or byproviding an image. RECipe consists of 3 subsystems: (1) behavior-basedrecommender, (2) review-based recommender, and (3) image-based recommender.Each subsystem relies on the embedding representations of entities andrelations in the graph. We first obtain (pre-trained) embedding representationsof textual entities, such as reviews or ingredients, from a fine-tuned model ofMicrosoft's MPNet. We initialize the weights of the entities with theseembeddings to train our knowledge graph embedding (KGE) model. For the visualcomponent, i.e., recipe images, we develop a KGE-Guided variational autoencoder(KG-VAE) to learn the distribution of images and their latent representations.Once KGE and KG-VAE models are fully trained, we use them as a multi-purposerecommendation framework. For benchmarking, we created two knowledge graphs(KGs) from public datasets on Kaggle for recipe recommendation. Our experimentsshow that the KGE models have comparable performance to the neural solutions.We also present pre-trained NLP embeddings to address important applicationssuch as zero-shot inference for new users (or the cold start problem) andconditional recommendation with respect to recipe categories. We eventuallydemonstrate the application of RECipe in a multi-purpose recommendationsetting.

RECipe: Does a Multi-Modal Recipe Knowledge Graph Fit a Multi-Purpose Recommendation System?