[4L2-GS-4] Web intelligence

[4L2-GS-4-05] Proposal on Finding Possible Menus Using Knowledge Graph Embeddings from Recipe Dataset

〇Aoi Ohta¹, Hiroki Shibata¹, Yasufumi Takama¹ (1. Tokyo Metropolitan University)

Keywords:knowledge graph embedding, recommendation, recipe recommendation

This paper proposes a method to find possible menus which do not explicitly exist in the recipe dataset using knowledge graph embedding (KGE). KGE can predict the invisible links in Knowledge Graphs (KGs) by representing each entity and relation as a vector. Using this feature, the proposed method finds invisible menus from the recipe dataset. As it is impossible for a recipe KG to include all possible combinations of recipes that could be regarded as menus, finding possible but invisible menus is necessary for realizing recipe recommender systems. This paper describes how to construct the recipe KG from Cookpad dataset and find potentially possible menus by exploiting TransE. The effectiveness of the proposed method is shown based on the survey-based evaluation.